The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical for cutting-edge commercial LLMs. Moreover, prevailing prompting methods depend on external tool feedback and fail to simultaneously lessen toxicity and bias. Motivated by social psychology principles, we propose a novel strategy named perspective-taking prompting (PeT) that inspires LLMs to integrate diverse human perspectives and self-regulate their responses. This self-correction mechanism can significantly diminish toxicity (up to 89%) and bias (up to 73%) in LLMs’ responses. Rigorous evaluations and ablation studies are conducted on two commercial LLMs (ChatGPT and GLM) and three open-source LLMs, revealing PeT’s superiority in producing less harmful responses, outperforming five strong baselines.

This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and reviewing available solutions, this survey aims to shed light on strategies for improving the robustness of LLMs, thereby serving as a valuable resource for advancing research in this evolving area.

We present a comprehensive evaluation of large language models for multilingual readability assessment. Existing evaluation resources lack domain and language diversity, limiting the ability for cross-domain and cross-lingual analyses. This paper introduces ReadMe++, a multilingual multi-domain dataset with human annotations of 9757 sentences in Arabic, English, French, Hindi, and Russian, collected from 112 different data sources. This benchmark will encourage research on developing robust multilingual readability assessment methods. Using ReadMe++, we benchmark multilingual and monolingual language models in the supervised, unsupervised, and few-shot prompting settings. The domain and language diversity in ReadMe++ enable us to test more effective few-shot prompting, and identify shortcomings in state-of-the-art unsupervised methods. Our experiments also reveal exciting results of superior domain generalization and enhanced cross-lingual transfer capabilities by models trained on ReadMe++. We will make our data publicly available and release a python package tool for multilingual sentence readability prediction using our trained models at: https://github.com/tareknaous/readme

Vision Language Models (VLMs) are rapidly advancing in their capability to answer information-seeking questions. As these models are widely deployed in consumer applications, they could lead to new privacy risks due to emergent abilities to identify people in photos, geolocate images, etc. As we demonstrate, somewhat surprisingly, current open-source and proprietary VLMs are very capable image geolocators, making widespread geolocation with VLMs an immediate privacy risk, rather than merely a theoretical future concern. As a first step to address this challenge, we develop a new benchmark, GPTGeoChat, to test the capability of VLMs to moderate geolocation dialogues with users. We collect a set of 1,000 image geolocation conversations between in-house annotators and GPT-4v, which are annotated with the granularity of location information revealed at each turn. Using this new dataset we evaluate the ability of various VLMs to moderate GPT-4v geolocation conversations by determining when too much location information has been revealed. We find that custom fine-tuned models perform on par with prompted API-based models when identifying leaked location information at the country or city level, however fine-tuning on supervised data appears to be needed to accurately moderate finer granularities, such as the name of a restaurant or building.

Medical texts are notoriously challenging to read. Properly measuring their readability is the first step towards making them more accessible. Here, we present the first systematic study on fine-grained readability measurements in the medical domain, at both sentence-level and span-level. We first introduce a new dataset MedReadMe, which consists of manually annotated readability ratings and fine-grained complex span annotation for 4,520 sentences, featuring two novel “Google-Easy” and “Google-Hard” categories. It supports our quantitative analysis, which covers 650 linguistic features and additional complex span features, to answer “why medical sentences are so hard.” Enabled by our high-quality annotation, we benchmark several state-of-the-art sentence-level readability metrics, including unsupervised, supervised, and prompting-based methods using recently developed large language models (LLMs). Informed by our fine-grained complex span annotation, we find that adding a single feature, capturing the number of jargon spans, into existing readability formulas can significantly improve their correlation with human judgments, and also make them more stable. We will publicly release data and code.

Research on jailbreaking has been valuable for testing and understanding the safety and security issues of large language models (LLMs). In this paper, we introduce Iterative Refinement Induced Self-Jailbreak (IRIS), a novel approach that leverages the reflective capabilities of LLMs for jailbreaking with only black-box access. Unlike previous methods, IRIS simplifies the jailbreaking process by using a single model as both the attacker and target. This method first iteratively refines adversarial prompts through self-explanation, which is crucial for ensuring that even well-aligned LLMs obey adversarial instructions. IRIS then rates and enhances the output given the refined prompt to increase its harmfulness. We find that IRIS achieves jailbreak success rates of 98% on GPT-4, 92% on GPT-4 Turbo, and 94% on Llama-3.1-70B in under 7 queries. It significantly outperforms prior approaches in automatic, black-box, and interpretable jailbreaking, while requiring substantially fewer queries, thereby establishing a new standard for interpretable jailbreaking methods.

While instruction fine-tuned LLMs are effective text generators, sensitivity to prompt construction makes performance unstable and sub-optimal in practice. Relying on a single ‘best’ prompt cannot capture all differing approaches to a generation problem. Using this observation, we propose multi-prompt decoding, where many candidate generations are decoded from a prompt bank at inference-time. To ensemble candidates, we use Minimum Bayes Risk (MBR) decoding, which selects a final output using a trained value metric. We show multi-prompt improves MBR across a comprehensive set of conditional generation tasks, and show this is a result of estimating a more diverse and higher quality candidate space than that of a single prompt. Our experiments confirm multi-prompt improves generation across tasks, models and metrics.

We introduce ChatHF, an interactive annotation framework for chatbot evaluation, which integrates configurable annotation within a chat interface. ChatHF can be flexibly configured to accommodate various chatbot evaluation tasks, for example detecting offensive content, identifying incorrect or misleading information in chatbot responses, and chatbot responses that might compromise privacy. It supports post-editing of chatbot outputs and supports visual inputs, in addition to an optional voice interface. ChatHF is suitable for collection and annotation of NLP datasets, and Human-Computer Interaction studies, as demonstrated in case studies on image geolocation and assisting older adults with daily activities. ChatHF is publicly accessible at https://chat-hf.com.

The risk of harmful contents generated by large language models (LLMs) becomes a critical concern. This paper systematically evaluates and enhances LLMs’ capability to perform course-correction, , the model can steer away from generating harmful content autonomously. First, we introduce the C²-Eval benchmark for quantitative assessment and analyze 10 popular LLMs, revealing varying proficiency of current safety-tuned LLMs in course-correction.To improve, we propose fine-tuning LLMs with preference learning, emphasizing the preference for timely course-correction. Using an automated pipeline, we create C²-Syn, a synthetic C²-Syn with 750K pairwise preferences, to teach models the concept of timely course-correction through data-driven learning.Experiments on Llama2-Chat 7B and Qwen2 7B show that our method effectively enhances course-correction skills without affecting general performance. Additionally, it effectively improves LLMs’ safety, particularly in resisting jailbreak attacks.

The Stanceosaurus corpus (Zheng et al., 2022) was designed to provide high-quality, annotated, 5-way stance data extracted from Twitter, suitable for analyzing cross-cultural and cross-lingual misinformation. In the Stanceosaurus 2.0 iteration, we extend this framework to encompass Russian and Spanish. The former is of current significance due to prevalent misinformation amid escalating tensions with the West and the violent incursion into Ukraine. The latter, meanwhile, represents an enormous community that has been largely overlooked on major social media platforms. By incorporating an additional 3,874 Spanish and Russian tweets over 41 misinformation claims, our objective is to support research focused on these issues. To demonstrate the value of this data, we employed zero-shot cross-lingual transfer on multilingual BERT, yielding results on par with the initial Stanceosaurus study with a macro F1 score of 43 for both languages. This underlines the viability of stance classification as an effective tool for identifying multicultural misinformation.

Finding interpretable factors for stock returns is the most vital issue in the empirical asset pricing domain. As data-driven methods, existing factor mining models can be categorized into symbol-based and neural-based models. Symbol-based models are interpretable but inefficient, while neural-based approaches are efficient but lack interpretability. Hence, mining interpretable factors effectively presents a significant challenge. Inspired by the success of Large Language Models (LLMs) in various tasks, we propose a FActor Mining Agent (FAMA) model that enables LLMs to integrate the strengths of both neural and symbolic models for factor mining. In this paper, FAMA consists of two main components: Cross-Sample Selection (CSS) and Chain-of-Experience (CoE). CSS addresses the homogeneity challenges in LLMs during factor mining by assimilating diverse factors as in-context samples, whereas CoE enables LLMs to leverage past successful mining experiences, expediting the mining of effective factors. Experimental evaluations on real-world stock market data demonstrate the effectiveness of our approach by surpassing the SOTA RankIC by 0.006 and RankICIR by 0.105 in predicting S&P 500 returns. Furthermore, the investment simulation shows that our model can achieve superior performance with an annualized return of 38.4% and a Sharpe ratio of 667.2%.

Large language models (LLMs) showcase impressive reasoning capabilities when coupled with Chain-of-Thought (CoT) prompting. However, the robustness of this approach warrants further investigation. In this paper, we introduce a novel scenario termed preemptive answers, where the LLM obtains an answer before engaging in reasoning. This situation can arise inadvertently or induced by malicious users by prompt injection attacks. Experiments reveal that preemptive answers significantly impair the model’s reasoning capability across various CoT methods and a broad spectrum of datasets. To bolster the robustness of reasoning, we propose two measures aimed at mitigating this issue to some extent.

Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. This work proposes InfoLossQA, a framework to characterize and recover simplification-induced information loss in form of question-and-answer (QA) pairs. Building on the theory of Questions Under Discussion, the QA pairs are designed to help readers deepen their knowledge of a text. First, we collect a dataset of 1,000 linguist-curated QA pairs derived from 104 LLM simplifications of English medical study abstracts. Our analyses of this data reveal that information loss occurs frequently, and that the QA pairs give a high-level overview of what information was lost. Second, we devise two methods for this task: end-to-end prompting of open-source and commercial language models, and a natural language inference pipeline. With a novel evaluation framework considering the correctness of QA pairs and their linguistic suitability, our expert evaluation reveals that models struggle to reliably identify information loss and applying similar standards as humans at what constitutes information loss.

Plain language summarization with LLMs can be useful for improving textual accessibility of technical content. But how factual are these summaries in a high-stakes domain like medicine? This paper presents FactPICO, a factuality benchmark for plain language summarization of medical texts describing randomized controlled trials (RCTs), which are the basis of evidence-based medicine and can directly inform patient treatment. FactPICO consists of 345 plain language summaries of RCT abstracts generated from three LLMs (i.e., GPT-4, Llama-2, and Alpaca), with fine-grained evaluation and natural language rationales from experts. We assess the factuality of critical elements of RCTs in those summaries: Populations, Interventions, Comparators, Outcomes (PICO), as well as the reported findings concerning these. We also evaluate the correctness of the extra information (e.g., explanations) added by LLMs. Using FactPICO, we benchmark a range of existing factuality metrics, including the newly devised ones based on LLMs. We find that plain language summarization of medical evidence is still challenging, especially when balancing between simplicity and factuality, and that existing metrics correlate poorly with expert judgments on the instance level.

Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this challenge, we investigate whether LLMs can be meta-trained based on representative lexicons to recognize new styles they have not been fine-tuned on. Experiments on 13 established style classification tasks, as well as 63 novel tasks generated using LLMs, demonstrate that meta-training with style lexicons consistently improves zero-shot transfer across styles. We release the code and data at https://github.com/octaviaguo/Style-LLM.

Self-disclosure, while being common and rewarding in social media interaction, also poses privacy risks. In this paper, we take the initiative to protect the user-side privacy associated with online self-disclosure through detection and abstraction. We develop a taxonomy of 19 self-disclosure categories and curate a large corpus consisting of 4.8K annotated disclosure spans. We then fine-tune a language model for detection, achieving over 65% partial span F₁. We further conduct an HCI user study, with 82% of participants viewing the model positively, highlighting its real-world applicability. Motivated by the user feedback, we introduce the task of self-disclosure abstraction, which is rephrasing disclosures into less specific terms while preserving their utility, e.g., “Im 16F” to “I’m a teenage girl”. We explore various fine-tuning strategies, and our best model can generate diverse abstractions that moderately reduce privacy risks while maintaining high utility according to human evaluation. To help users in deciding which disclosures to abstract, we present a task of rating their importance for context understanding. Our fine-tuned model achieves 80% accuracy, on-par with GPT-3.5. Given safety and privacy considerations, we will only release our corpus and models to researcher who agree to the ethical guidelines outlined in Ethics Statement.

The performance of Large Language Models (LLMs) degrades from the temporal drift between data used for model training and newer text seen during inference. One understudied avenue of language change causing data drift is the emergence of neologisms – new word forms – over time. We create a diverse resource of recent English neologisms by using several popular collection methods. We analyze temporal drift using neologisms by comparing sentences containing new words with near-identical sentences that replace neologisms with existing substitute words. Model performance is nearly halved in machine translation when a single neologism is introduced in a sentence. Motivated by these results, we construct a benchmark to evaluate LLMs’ ability to generalize to neologisms with various natural language understanding tasks and model perplexity. Models with later knowledge cutoff dates yield lower perplexities and perform better in downstream tasks. LLMs are also affected differently based on the linguistic origins of words, indicating that neologisms are complex for static LLMs to address. We will release our benchmark and code for reproducing our experiments.

Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-turn setting. However, belief can change during a multi-turn conversation, especially a persuasive one. Therefore, in this study, we delve into LLMs’ susceptibility to persuasive conversations, particularly on factual questions that they can answer correctly. We first curate the Farm (i.e., Fact to Misinform) dataset, which contains factual questions paired with systematically generated persuasive misinformation. Then, we develop a testing framework to track LLMs’ belief changes in a persuasive dialogue. Through extensive experiments, we find that LLMs’ correct beliefs on factual knowledge can be easily manipulated by various persuasive strategies.

As the reach of large language models (LMs) expands globally, their ability to cater to diverse cultural contexts becomes crucial. Despite advancements in multilingual capabilities, models are not designed with appropriate cultural nuances. In this paper, we show that multilingual and Arabic monolingual LMs exhibit bias towards entities associated with Western culture. We introduce CAMeL, a novel resource of 628 naturally-occurring prompts and 20,368 entities spanning eight types that contrast Arab and Western cultures. CAMeL provides a foundation for measuring cultural biases in LMs through both extrinsic and intrinsic evaluations. Using CAMeL, we examine the cross-cultural performance in Arabic of 16 different LMs on tasks such as story generation, NER, and sentiment analysis, where we find concerning cases of stereotyping and cultural unfairness. We further test their text-infilling performance, revealing the incapability of appropriate adaptation to Arab cultural contexts. Finally, we analyze 6 Arabic pre-training corpora and find that commonly used sources such as Wikipedia may not be best suited to build culturally aware LMs, if used as they are without adjustment. We will make CAMeL publicly available at: https://github.com/tareknaous/camel

In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e.g., readability or linguistic styles), while largely retaining the original meaning and the length of the text. This includes many useful applications, such as text simplification, paraphrase generation, style transfer, etc. In contrast to text summarization and open-ended text completion (e.g., story), the text-to-text generation tasks we discuss in this tutorial are more constrained in terms of semantic consistency and targeted language styles. This level of control makes these tasks ideal testbeds for studying the ability of models to generate text that is both semantically adequate and stylistically appropriate. Moreover, these tasks are interesting from a technical standpoint, as they require complex combinations of lexical and syntactical transformations, stylistic control, and adherence to factual knowledge, – all at once. With a special focus on text simplification and revision, this tutorial aims to provide an overview of the state-of-the-art natural language generation research from four major aspects – Data, Models, Human-AI Collaboration, and Evaluation – and to discuss and showcase a few significant and recent advances: (1) the use of non-retrogressive approaches; (2) the shift from fine-tuning to prompting with large language models; (3) the development of new learnable metric and fine-grained human evaluation framework; (4) a growing body of studies and datasets on non-English languages; (5) the rise of HCI+NLP+Accessibility interdisciplinary research to create real-world writing assistant systems.

Recent advancements in high-quality, large-scale English resources have pushed the frontier of English Automatic Text Simplification (ATS) research. However, less work has been done on multilingual text simplification due to the lack of a diverse evaluation benchmark that covers complex-simple sentence pairs in many languages. This paper introduces the MultiSim benchmark, a collection of 27 resources in 12 distinct languages containing over 1.7 million complex-simple sentence pairs. This benchmark will encourage research in developing more effective multilingual text simplification models and evaluation metrics. Our experiments using MultiSim with pre-trained multilingual language models reveal exciting performance improvements from multilingual training in non-English settings. We observe strong performance from Russian in zero-shot cross-lingual transfer to low-resource languages. We further show that few-shot prompting with BLOOM-176b achieves comparable quality to reference simplifications outperforming fine-tuned models in most languages. We validate these findings through human evaluation.

In this paper, we study the task of instructional dialogue and focus on the cooking domain. Analyzing the generated output of the GPT-J model, we reveal that the primary challenge for a recipe-grounded dialog system is how to provide the instructions in the correct order. We hypothesize that this is due to the model’s lack of understanding of user intent and inability to track the instruction state (i.e., which step was last instructed). Therefore, we propose to explore two auxiliary subtasks, namely User Intent Detection and Instruction State Tracking, to support Response Generation with improved instruction grounding. Experimenting with our newly collected dataset, ChattyChef, shows that incorporating user intent and instruction state information helps the response generation model mitigate the incorrect order issue. Furthermore, to investigate whether ChatGPT has completely solved this task, we analyze its outputs and find that it also makes mistakes (10.7% of the responses), about half of which are out-of-order instructions. We will release ChattyChef to facilitate further research in this area at: https://github.com/octaviaguo/ChattyChef.

Fine-tuning large models is highly effective, however, inference can be expensive and produces carbon emissions. Knowledge distillation has been shown to be a practical solution to reduce inference costs, but the distillation process itself requires significant computational resources. Rather than buying or renting GPUs to fine-tune, then distill a large model, an NLP practitioner might instead choose to allocate the available budget to hire annotators and manually label additional fine-tuning data. In this paper, we investigate how to most efficiently use a fixed budget to build a compact model. Through extensive experiments on six diverse tasks, we show that distilling from T5-XXL (11B) to T5-Small (60M) is almost always a cost-efficient strategy compared to annotating more data to directly train a compact model (T5-Small). We further investigate how the optimal budget allocated towards computation varies across scenarios. We will make our code, datasets, annotation cost estimates, and baseline models available as a benchmark to support further work on cost-efficient training of compact models.

We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that support them. Our approach extracts check-worthy claims, which are aggregated and ranked for review. Stance classifiers are then used to identify tweets supporting novel misinformation claims, which are further reviewed to determine whether they violate relevant policies. To demonstrate the feasibility of our approach, we develop a baseline system based on modern NLP methods for human-in-the-loop fact-checking in the domain of COVID-19 treatments. We make our data and detailed annotation guidelines available to support the evaluation of human-in-the-loop systems that identify novel misinformation directly from raw user-generated content.

Training learnable metrics using modern language models has recently emerged as a promising method for the automatic evaluation of machine translation. However, existing human evaluation datasets for text simplification have limited annotations that are based on unitary or outdated models, making them unsuitable for this approach. To address these issues, we introduce the SimpEval corpus that contains: SimpEval_past, comprising 12K human ratings on 2.4K simplifications of 24 past systems, and SimpEval_2022, a challenging simplification benchmark consisting of over 1K human ratings of 360 simplifications including GPT-3.5 generated text. Training on SimpEval, we present LENS, a Learnable Evaluation Metric for Text Simplification. Extensive empirical results show that LENS correlates much better with human judgment than existing metrics, paving the way for future progress in the evaluation of text simplification. We also introduce Rank & Rate, a human evaluation framework that rates simplifications from several models in a list-wise manner using an interactive interface, which ensures both consistency and accuracy in the evaluation process and is used to create the SimpEval datasets.

Translating training data into many languages has emerged as a practical solution for improving cross-lingual transfer. For tasks that involve span-level annotations, such as information extraction or question answering, an additional label projection step is required to map annotated spans onto the translated texts. Recently, a few efforts have utilized a simple mark-then-translate method to jointly perform translation and projection by inserting special markers around the labeled spans in the original sentence. However, as far as we are aware, no empirical analysis has been conducted on how this approach compares to traditional annotation projection based on word alignment. In this paper, we present an extensive empirical study across 57 languages and three tasks (QA, NER, and Event Extraction) to evaluate the effectiveness and limitations of both methods, filling an important gap in the literature. Experimental results show that our optimized version of mark-then-translate, which we call EasyProject, is easily applied to many languages and works surprisingly well, outperforming the more complex word alignment-based methods. We analyze several key factors that affect the end-task performance, and show EasyProject works well because it can accurately preserve label span boundaries after translation. We will publicly release all our code and data.

Randomly masking text spans in ordinary texts in the pre-training stage hardly allows models to acquire the ability to generate simple texts. It can hurt the performance of pre-trained models on text simplification tasks. In this paper, we propose a new continued pre-training strategy to teach the pre-trained model to generate simple texts. We continue pre-training BART, a representative model, to obtain SimpleBART. It consistently and significantly improves the results on lexical simplification, sentence simplification, and document-level simplification tasks over BART. At the end, we compare SimpleBART with several representative large language models (LLMs).

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user’s plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p < 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p < 0.05) in a low-data setting.

Large language models (e.g., GPT-4) are uniquely capable of producing highly rated text simplification, yet current human evaluation methods fail to provide a clear understanding of systems’ specific strengths and weaknesses. To address this limitation, we introduce SALSA, an edit-based human annotation framework that enables holistic and fine-grained text simplification evaluation. We develop twenty one linguistically grounded edit types, covering the full spectrum of success and failure across dimensions of conceptual, syntactic and lexical simplicity. Using SALSA, we collect 19K edit annotations on 840 simplifications, revealing discrepancies in the distribution of simplification strategies performed by fine-tuned models, prompted LLMs and humans, and find GPT-3.5 performs more quality edits than humans, but still exhibits frequent errors. Using our fine-grained annotations, we develop LENS-SALSA, a reference-free automatic simplification metric, trained to predict sentence- and word-level quality simultaneously. Additionally, we introduce word-level quality estimation for simplification and report promising baseline results. Our data, new metric, and annotation toolkit are available at https://salsa-eval.com.

Automated text simplification aims to produce simple versions of complex texts. This task is especially useful in the medical domain, where the latest medical findings are typically communicated via complex and technical articles. This creates barriers for laypeople seeking access to up-to-date medical findings, consequently impeding progress on health literacy. Most existing work on medical text simplification has focused on monolingual settings, with the result that such evidence would be available only in just one language (most often, English). This work addresses this limitation via multilingual simplification, i.e., directly simplifying complex texts into simplified texts in multiple languages. We introduce MultiCochrane, the first sentence-aligned multilingual text simplification dataset for the medical domain in four languages: English, Spanish, French, and Farsi. We evaluate fine-tuned and zero-shot models across these languages with extensive human assessments and analyses. Although models can generate viable simplified texts, we identify several outstanding challenges that this dataset might be used to address.

Fine-grained, span-level human evaluation has emerged as a reliable and robust method for evaluating text generation tasks such as summarization, simplification, machine translation and news generation, and the derived annotations have been useful for training automatic metrics and improving language models. However, existing annotation tools implemented for these evaluation frameworks lack the adaptability to be extended to different domains or languages, or modify annotation settings according to user needs; and, the absence of a unified annotated data format inhibits the research in multi-task learning. In this paper, we introduce Thresh, a unified, customizable and deployable platform for fine-grained evaluation. With a single YAML configuration file, users can build and test an annotation interface for any framework within minutes – all in one web browser window. To facilitate collaboration and sharing, Thresh provides a community hub that hosts a collection of fine-grained frameworks and corresponding annotations made and collected by the community, covering a wide range of NLP tasks. For deployment, Thresh offers multiple options for any scale of annotation projects from small manual inspections to large crowdsourcing ones. Additionally, we introduce a Python library to streamline the entire process from typology design and deployment to annotation processing. Thresh is publicly accessible at https://thresh.tools.

Research has explored the use of automatic text simplification (ATS), which consists of techniques to make text simpler to read, to provide reading assistance to Deaf and Hard-of-hearing (DHH) adults with various literacy levels. Prior work in this area has identified interest in and benefits from ATS-based reading assistance tools. However, no prior work on ATS has gathered judgements from DHH adults as to what constitutes complex text. Thus, following approaches in prior NLP work, this paper contributes new word-complexity judgements from 11 DHH adults on a dataset of 15,000 English words that had been previously annotated by L2 speakers, which we also augmented to include automatic annotations of linguistic characteristics of the words. Additionally, we conduct a supplementary analysis of the interaction effect between the linguistic characteristics of the words and the groups of annotators. This analysis highlights the importance of collecting judgements from DHH adults for training ATS systems, as it revealed statistically significant interaction effects for nearly all of the linguistic characteristics of the words.

We present Stanceosaurus, a new corpus of 28,033 tweets in English, Hindi and Arabic annotated with stance towards 250 misinformation claims. As far as we are aware, it is the largest corpus annotated with stance towards misinformation claims. The claims in Stanceosaurus originate from 15 fact-checking sources that cover diverse geographical regions and cultures. Unlike existing stance datasets, we introduce a more fine-grained 5-class labeling strategy with additional subcategories to distinguish implicit stance. Pre-trained transformer-based stance classifiers that are fine-tuned on our corpus show good generalization on unseen claims and regional claims from countries outside the training data. Cross-lingual experiments demonstrate Stanceosaurus’ capability of training multilingual models, achieving 53.1 F1 on Hindi and 50.4 F1 on Arabic without any target-language fine-tuning. Finally, we show how a domain adaptation method can be used to improve performance on Stanceosaurus using additional RumourEval-2019 data. We will make Stanceosaurus publicly available to the research community upon publication and hope it will encourage further work on misinformation identification across languages and cultures.

This paper addresses the quality issues in existing Twitter-based paraphrase datasets, and discusses the necessity of using two separate definitions of paraphrase for identification and generation tasks. We present a new Multi-Topic Paraphrase in Twitter (MultiPIT) corpus that consists of a total of 130k sentence pairs with crowdsoursing (MultiPIT_crowd) and expert (MultiPIT_expert) annotations using two different paraphrase definitions for paraphrase identification, in addition to a multi-reference test set (MultiPIT_NMR) and a large automatically constructed training set (MultiPIT_Auto) for paraphrase generation. With improved data annotation quality and task-specific paraphrase definition, the best pre-trained language model fine-tuned on our dataset achieves the state-of-the-art performance of 84.2 F1 for automatic paraphrase identification. Furthermore, our empirical results also demonstrate that the paraphrase generation models trained on MultiPIT_Auto generate more diverse and high-quality paraphrases compared to their counterparts fine-tuned on other corpora such as Quora, MSCOCO, and ParaNMT.

Scientific publications are the primary means to communicate research discoveries, where the writing quality is of crucial importance. However, prior work studying the human editing process in this domain mainly focused on the abstract or introduction sections, resulting in an incomplete picture. In this work, we provide a complete computational framework for studying text revision in scientific writing. We first introduce arXivEdits, a new annotated corpus of 751 full papers from arXiv with gold sentence alignment across their multiple versions of revision, as well as fine-grained span-level edits and their underlying intentions for 1,000 sentence pairs. It supports our data-driven analysis to unveil the common strategies practiced by researchers for revising their papers. To scale up the analysis, we also develop automatic methods to extract revision at document-, sentence-, and word-levels. A neural CRF sentence alignment model trained on our corpus achieves 93.8 F1, enabling the reliable matching of sentences between different versions. We formulate the edit extraction task as a span alignment problem, and our proposed method extracts more fine-grained and explainable edits, compared to the commonly used diff algorithm. An intention classifier trained on our dataset achieves 78.9 F1 on the fine-grained intent classification task. Our data and system are released at tiny.one/arxivedits.

We present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 28 fine-grained slots, such as the location of events, recent travel, and close contacts. We show that our corpus can support fine-tuning BERT-based classifiers to automatically extract publicly reported events, which can be further collected for building a knowledge base. Our knowledge base is constructed over Twitter data covering two years and currently covers over 4.2M events. It can answer complex queries with high precision, such as “Which organizations have employees that tested positive in Philadelphia?” We believe our proposed methodology could be quickly applied to develop knowledge bases for new domains in response to an emerging crisis, including natural disasters or future disease outbreaks.

Monolingual word alignment is important for studying fine-grained editing operations (i.e., deletion, addition, and substitution) in text-to-text generation tasks, such as paraphrase generation, text simplification, neutralizing biased language, etc. In this paper, we present a novel neural semi-Markov CRF alignment model, which unifies word and phrase alignments through variable-length spans. We also create a new benchmark with human annotations that cover four different text genres to evaluate monolingual word alignment models in more realistic settings. Experimental results show that our proposed model outperforms all previous approaches for monolingual word alignment as well as a competitive QA-based baseline, which was previously only applied to bilingual data. Our model demonstrates good generalizability to three out-of-domain datasets and shows great utility in two downstream applications: automatic text simplification and sentence pair classification tasks.

Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to perform all these operations simultaneously. However, such systems limit themselves to mostly deleting words and cannot easily adapt to the requirements of different target audiences. In this paper, we propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles. We introduce a new data augmentation method to improve the paraphrasing capability of our model. Through automatic and manual evaluations, we show that our proposed model establishes a new state-of-the-art for the task, paraphrasing more often than the existing systems, and can control the degree of each simplification operation applied to the input texts.

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for the 2021 shared task at the associated GEM Workshop.

Biases continue to be prevalent in modern text and media, especially subjective bias – a special type of bias that introduces improper attitudes or presents a statement with the presupposition of truth. To tackle the problem of detecting and further mitigating subjective bias, we introduce a manually annotated parallel corpus WIKIBIAS with more than 4,000 sentence pairs from Wikipedia edits. This corpus contains annotations towards both sentence-level bias types and token-level biased segments. We present systematic analyses of our dataset and results achieved by a set of state-of-the-art baselines in terms of three tasks: bias classification, tagging biased segments, and neutralizing biased text. We find that current models still struggle with detecting multi-span biases despite their reasonable performances, suggesting that our dataset can serve as a useful research benchmark. We also demonstrate that models trained on our dataset can generalize well to multiple domains such as news and political speeches.

Recent work has demonstrated that pre-training in-domain language models can boost performance when adapting to a new domain. However, the costs associated with pre-training raise an important question: given a fixed budget, what steps should an NLP practitioner take to maximize performance? In this paper, we study domain adaptation under budget constraints, and approach it as a customer choice problem between data annotation and pre-training. Specifically, we measure the annotation cost of three procedural text datasets and the pre-training cost of three in-domain language models. Then we evaluate the utility of different combinations of pre-training and data annotation under varying budget constraints to assess which combination strategy works best. We find that, for small budgets, spending all funds on annotation leads to the best performance; once the budget becomes large enough, a combination of data annotation and in-domain pre-training works more optimally. We therefore suggest that task-specific data annotation should be part of an economical strategy when adapting an NLP model to a new domain.

An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a new model for this ‘split and rephrase’ task. Our BiSECT training data consists of 1 million long English sentences paired with shorter, meaning-equivalent English sentences. We obtain these by extracting 1-2 sentence alignments in bilingual parallel corpora and then using machine translation to convert both sides of the corpus into the same language. BiSECT contains higher quality training examples than the previous Split and Rephrase corpora, with sentence splits that require more significant modifications. We categorize examples in our corpus and use these categories in a novel model that allows us to target specific regions of the input sentence to be split and edited. Moreover, we show that models trained on BiSECT can perform a wider variety of split operations and improve upon previous state-of-the-art approaches in automatic and human evaluations.

This paper presents the results of the wet labinformation extraction task at WNUT 2020.This task consisted of two sub tasks- (1) anamed entity recognition task with 13 partic-ipants; and (2) a relation extraction task with2 participants. We outline the task, data an-notation process, corpus statistics, and providea high-level overview of the participating sys-tems for each sub task.

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. We perform extensive experiments to test this insight on 10 disparate tasks spanning dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving performance comparable to state-of-the-art specialized models. We further demonstrate benefits of multi-task learning, and also show that the proposed method makes it easy to analyze differences and similarities in how the model handles different tasks. Finally, we convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.

There is an increasing interest in studying natural language and computer code together, as large corpora of programming texts become readily available on the Internet. For example, StackOverflow currently has over 15 million programming related questions written by 8.5 million users. Meanwhile, there is still a lack of fundamental NLP techniques for identifying code tokens or software-related named entities that appear within natural language sentences. In this paper, we introduce a new named entity recognition (NER) corpus for the computer programming domain, consisting of 15,372 sentences annotated with 20 fine-grained entity types. We trained in-domain BERT representations (BERTOverflow) on 152 million sentences from StackOverflow, which lead to an absolute increase of +10 F1 score over off-the-shelf BERT. We also present the SoftNER model which achieves an overall 79.10 F-1 score for code and named entity recognition on StackOverflow data. Our SoftNER model incorporates a context-independent code token classifier with corpus-level features to improve the BERT-based tagging model. Our code and data are available at: https://github.com/jeniyat/StackOverflowNER/

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity. Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1. We apply our CRF aligner to construct two new text simplification datasets, Newsela-Auto and Wiki-Auto, which are much larger and of better quality compared to the existing datasets. A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation.

Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable effective cross-lingual zero-shot transfer. However, their performance on Arabic information extraction (IE) tasks is not very well studied. In this paper, we pre-train a customized bilingual BERT, dubbed GigaBERT, that is designed specifically for Arabic NLP and English-to-Arabic zero-shot transfer learning. We study GigaBERT’s effectiveness on zero-short transfer across four IE tasks: named entity recognition, part-of-speech tagging, argument role labeling, and relation extraction. Our best model significantly outperforms mBERT, XLM-RoBERTa, and AraBERT (Antoun et al., 2020) in both the supervised and zero-shot transfer settings. We have made our pre-trained models publicly available at: https://github.com/lanwuwei/GigaBERT.

Pattern-based labeling methods have achieved promising results in alleviating the inevitable labeling noises of distantly supervised neural relation extraction. However, these methods require significant expert labor to write relation-specific patterns, which makes them too sophisticated to generalize quickly. To ease the labor-intensive workload of pattern writing and enable the quick generalization to new relation types, we propose a neural pattern diagnosis framework, DIAG-NRE, that can automatically summarize and refine high-quality relational patterns from noise data with human experts in the loop. To demonstrate the effectiveness of DIAG-NRE, we apply it to two real-world datasets and present both significant and interpretable improvements over state-of-the-art methods.

Hashtags are often employed on social media and beyond to add metadata to a textual utterance with the goal of increasing discoverability, aiding search, or providing additional semantics. However, the semantic content of hashtags is not straightforward to infer as these represent ad-hoc conventions which frequently include multiple words joined together and can include abbreviations and unorthodox spellings. We build a dataset of 12,594 hashtags split into individual segments and propose a set of approaches for hashtag segmentation by framing it as a pairwise ranking problem between candidate segmentations. Our novel neural approaches demonstrate 24.6% error reduction in hashtag segmentation accuracy compared to the current state-of-the-art method. Finally, we demonstrate that a deeper understanding of hashtag semantics obtained through segmentation is useful for downstream applications such as sentiment analysis, for which we achieved a 2.6% increase in average recall on the SemEval 2017 sentiment analysis dataset.

Most existing event extraction (EE) methods merely extract event arguments within the sentence scope. However, such sentence-level EE methods struggle to handle soaring amounts of documents from emerging applications, such as finance, legislation, health, etc., where event arguments always scatter across different sentences, and even multiple such event mentions frequently co-exist in the same document. To address these challenges, we propose a novel end-to-end model, Doc2EDAG, which can generate an entity-based directed acyclic graph to fulfill the document-level EE (DEE) effectively. Moreover, we reformalize a DEE task with the no-trigger-words design to ease the document-level event labeling. To demonstrate the effectiveness of Doc2EDAG, we build a large-scale real-world dataset consisting of Chinese financial announcements with the challenges mentioned above. Extensive experiments with comprehensive analyses illustrate the superiority of Doc2EDAG over state-of-the-art methods. Data and codes can be found at https://github.com/dolphin-zs/Doc2EDAG.

We describe an effort to annotate a corpus of natural language instructions consisting of 622 wet lab protocols to facilitate automatic or semi-automatic conversion of protocols into a machine-readable format and benefit biological research. Experimental results demonstrate the utility of our corpus for developing machine learning approaches to shallow semantic parsing of instructional texts. We make our annotated Wet Lab Protocol Corpus available to the research community.

Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and compose sentence-level semantics in varied ways; however, few works have attempted to verify whether we really need pretrained embeddings in these tasks. In this paper, we study how effective subword-level (character and character n-gram) representations are in sentence pair modeling. Though it is well-known that subword models are effective in tasks with single sentence input, including language modeling and machine translation, they have not been systematically studied in sentence pair modeling tasks where the semantic and string similarities between texts matter. Our experiments show that subword models without any pretrained word embedding can achieve new state-of-the-art results on two social media datasets and competitive results on news data for paraphrase identification.

Building intelligent agents that can communicate with and learn from humans in natural language is of great value. Supervised language learning is limited by the ability of capturing mainly the statistics of training data, and is hardly adaptive to new scenarios or flexible for acquiring new knowledge without inefficient retraining or catastrophic forgetting. We highlight the perspective that conversational interaction serves as a natural interface both for language learning and for novel knowledge acquisition and propose a joint imitation and reinforcement approach for grounded language learning through an interactive conversational game. The agent trained with this approach is able to actively acquire information by asking questions about novel objects and use the just-learned knowledge in subsequent conversations in a one-shot fashion. Results compared with other methods verified the effectiveness of the proposed approach.

In this paper, we analyze several neural network designs (and their variations) for sentence pair modeling and compare their performance extensively across eight datasets, including paraphrase identification, semantic textual similarity, natural language inference, and question answering tasks. Although most of these models have claimed state-of-the-art performance, the original papers often reported on only one or two selected datasets. We provide a systematic study and show that (i) encoding contextual information by LSTM and inter-sentence interactions are critical, (ii) Tree-LSTM does not help as much as previously claimed but surprisingly improves performance on Twitter datasets, (iii) the Enhanced Sequential Inference Model is the best so far for larger datasets, while the Pairwise Word Interaction Model achieves the best performance when less data is available. We release our implementations as an open-source toolkit.

Current lexical simplification approaches rely heavily on heuristics and corpus level features that do not always align with human judgment. We create a human-rated word-complexity lexicon of 15,000 English words and propose a novel neural readability ranking model with a Gaussian-based feature vectorization layer that utilizes these human ratings to measure the complexity of any given word or phrase. Our model performs better than the state-of-the-art systems for different lexical simplification tasks and evaluation datasets. Additionally, we also produce SimplePPDB++, a lexical resource of over 10 million simplifying paraphrase rules, by applying our model to the Paraphrase Database (PPDB).

A major challenge in paraphrase research is the lack of parallel corpora. In this paper, we present a new method to collect large-scale sentential paraphrases from Twitter by linking tweets through shared URLs. The main advantage of our method is its simplicity, as it gets rid of the classifier or human in the loop needed to select data before annotation and subsequent application of paraphrase identification algorithms in the previous work. We present the largest human-labeled paraphrase corpus to date of 51,524 sentence pairs and the first cross-domain benchmarking for automatic paraphrase identification. In addition, we show that more than 30,000 new sentential paraphrases can be easily and continuously captured every month at ~70% precision, and demonstrate their utility for downstream NLP tasks through phrasal paraphrase extraction. We make our code and data freely available.

As natural language processing research is growing and largely driven by the availability of data, we expanded research from news and small-scale dialog corpora to web and social media. User-generated data and crowdsourcing opened the door for investigating human language of various styles with more statistical power and real-world applications. In this position/survey paper, I will review and discuss seven language styles that I believe to be important and interesting to study: influential work in the past, challenges at the present, and potential impact for the future.

Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a performance gap between a single NMT model and the best conventional MT system. In this work, we introduce a new type of linear connections, named fast-forward connections, based on deep Long Short-Term Memory (LSTM) networks, and an interleaved bi-directional architecture for stacking the LSTM layers. Fast-forward connections play an essential role in propagating the gradients and building a deep topology of depth 16. On the WMT’14 English-to-French task, we achieve BLEU=37.7 with a single attention model, which outperforms the corresponding single shallow model by 6.2 BLEU points. This is the first time that a single NMT model achieves state-of-the-art performance and outperforms the best conventional model by 0.7 BLEU points. We can still achieve BLEU=36.3 even without using an attention mechanism. After special handling of unknown words and model ensembling, we obtain the best score reported to date on this task with BLEU=40.4. Our models are also validated on the more difficult WMT’14 English-to-German task.

Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantity of manually simplified corpora, which are expensive to build. In this paper, we conduct an in-depth adaptation of statistical machine translation to perform text simplification, taking advantage of large-scale paraphrases learned from bilingual texts and a small amount of manual simplifications with multiple references. Our work is the first to design automatic metrics that are effective for tuning and evaluating simplification systems, which will facilitate iterative development for this task.

This paper presents the results of the Twitter Named Entity Recognition shared task associated with W-NUT 2016: a named entity tagging task with 10 teams participating. We outline the shared task, annotation process and dataset statistics, and provide a high-level overview of the participating systems for each shared task.

Simple Wikipedia has dominated simplification research in the past 5 years. In this opinion paper, we argue that focusing on Wikipedia limits simplification research. We back up our arguments with corpus analysis and by highlighting statements that other researchers have made in the simplification literature. We introduce a new simplification dataset that is a significant improvement over Simple Wikipedia, and present a novel quantitative-comparative approach to study the quality of simplification data resources.

We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.