Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their mistakes. We develop the Chain-of-Verification (CoVe) method whereby the model first (i) drafts an initial response; then (ii) plans verification questions to fact-check its draft; (iii) answers those questions independently so the answers are not biased by other responses; and (iv) generates its final verified response. In experiments, we show CoVe decreases hallucinations across a variety of tasks, from list-based questions from Wikidata, closed book MultiSpanQA and longform text generation.

The impressive generation capabilities of large language models (LLMs) have made it harder to detect the subtle hallucinations they make in abstractive summarization, where generated summaries consist of a blend of correct and incorrect information w.r.t. a given document. Recently-proposed LLM-based evaluation metrics attempt to capture this, but still face challenges: (1) they are biased towards summaries generated from the same underlying LLM, and (2) they lack interpretability, offering only a single score. In this work, we present ACUEval, a metric that leverages the power of LLMs to perform two sub-tasks: decomposing summaries into atomic content units (ACUs), and validating them against the source document. Compared to current strong LLM-based metrics, our two-step evaluation strategy improves correlation with human judgments of faithfulness on three summarization evaluation benchmarks by 3% in balanced accuracy compared to the next-best metric, and also shows reduced preference bias towards LLM-generated summary. Further, we show that errors detected by ACUEval can be used to generate actionable feedback for refining the summary, improving the faithfulness scores by more than 10%.

Chain-of-thought (CoT) has impressively unlocked the reasoning potential of large language models (LLMs). Yet, it falls short when tackling problems that require multiple reasoning steps. This limitation arises from the complex nature of multi-step reasoning processes: later stages often depend not only on the immediately preceding step, but also on the results from several steps earlier. Such complexities indicate the reasoning process is naturally a graph. The almost linear structure of CoT, however, struggles to capture this complex reasoning graph. To address this challenge, we propose Residual Connection Prompting (ResPrompt), a new prompting strategy that advances multi-step reasoning in LLMs. The core of our idea is to reconstruct the reasoning graph within prompts. We achieve this by integrating necessary connections–links present in reasoning graph but missing in the linear CoT flow–into the prompts. Termed “residual connections”, these links can transform linear CoT into the complex reasoning graphs that multi-step problems entail. On benchmarks across math, sequential, and commonsense domains, ResPrompt demonstrates clear improvements in multi-step reasoning compared with CoT. Through extensive ablation studies and analyses, we pinpoint how to effectively build residual connections and also identify situations where it might be unnecessary.

Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations and self-improve?A popular concept, referred to as *self-refinement*, postulates that LLMs can detect and correct the errors in their generations when asked to do so. However, recent empirical evidence points in the opposite direction, suggesting that LLMs often struggle to accurately identify errors when reasoning is involved. To address this, we propose a reasoning with a refinement strategy called *ART: Ask, Refine, and Trust*, which *asks* necessary questions to decide when an LLM should *refine* its output, and uses it to affirm or deny *trust* in its refinement by ranking the refinement and the initial prediction. On two multistep reasoning tasks of mathematical word problems (GSM8K) and question answering (StrategyQA), *ART* achieves a performance gain of +5 points over self-refinement baselines, while using a much smaller model as the decision maker. We believe that *ART* with smaller models, making refinement decisions can be a cost-effective alternative to fine-tuning LLMs.

Large Language Models (LLMs) are frequently used for multi-faceted language generation and evaluation tasks that involve satisfying intricate user constraints or taking into account multiple aspects and criteria. However, their performance can fall short, due to the model’s lack of coherence and inability to plan and decompose the problem. We propose Branch-Solve-Merge (BSM), a Large Language Model program (Schlag et al., 2023) for tackling such challenging natural language tasks. It consists of branch, solve, and merge modules that are parameterized with specific prompts to the base LLM. These three modules plan a decomposition of the task into multiple parallel sub-tasks, independently solve them, and fuse the solutions to the sub-tasks. We apply our method to the tasks of LLM response evaluation and constrained text generation and evaluate its effectiveness with multiple LLMs, including Vicuna, LLaMA-2-chat, and GPT-4. BSM improves the evaluation correctness and consistency for each LLM by enhancing human-LLM agreement by up to 26%, reducing length and pairwise position biases by up to 50%, and allowing LLaMA-2-chat to match or outperform GPT-4 on most domains. On a constraint story generation task, BSM improves the coherence of stories while also improving constraint satisfaction by 12%.

Recent advancements in large language models have enabled them to perform well on complex tasks that require step-by-step reasoning with few-shot learning. However, it is unclear whether these models are applying reasoning skills they have learnt during pre-training , or if they are simply memorizing their training corpus at finer granularity and have learnt to better understand their context. To address this question, we introduce {pasted macro ‘OUR’}model, a benchmark and suite of analyses for evaluating reasoning skills of language models. {pasted macro ‘OUR’}model enables comparing pre-trained and finetuned models on complex tasks that require reasoning skills to solve. Our benchmark provides a test bed to asses any language model on fine-grained reasoning skills, which spans over 20 datasets and covers 10 different reasoning skills. By using {pasted macro ‘OUR’}model we further investigate the role of finetuning. Our extensive empirical analysis shows that language models learn more reasoning skills such as textual entailment, abductive reasoning, and analogical reasoning during the finetuning stage compared to pretraining stage. However, we also find that when language models are finetuned they tend to overfit to the prompt template, which hurts the robustness of models causing generalization problems.

In-context learning (ICL) improves language models’ performance on a variety of NLP tasks by simply demonstrating a handful of examples at inference time. It is not well understood why ICL ability emerges, as the model has never been specifically trained on such demonstrations. Unlike prior work that explores implicit mechanisms behind ICL, we study ICL via investigating the pretraining data. Specifically, we first adapt an iterative, gradient-based approach to find a small subset of pretraining data that supports ICL. We observe that a continued pretraining on this small subset significantly improves the model’s ICL ability, by up to 18%. We then compare the supportive subset constrastively with random subsets of pretraining data and discover: (1) The supportive pretraining data to ICL do not have a higher domain relevance to downstream tasks. (2) The supportive pretraining data have a higher mass of rarely occurring, long-tail tokens. (3) The supportive pretraining data are challenging examples where the information gain from long-range context is below average, indicating learning to incorporate difficult long-range context encourages ICL. Our work takes a first step towards understanding ICL via analyzing instance-level pretraining data. Our insights have a potential to enhance the ICL ability of language models by actively guiding the construction of pretraining data in the future.

Large language models (LLMs) have exhibited remarkable capabilities in learning from expla- nations in prompts, but there has been limited understanding of exactly how these explana- tions function or why they are effective. This work aims to better understand the mechanisms by which explanations are used for in-context learning. We first study the impact of two dif- ferent factors on the performance of prompts with explanations: the computation trace (the way the solution is decomposed) and the natural language used to express the prompt. By per- turbing explanations on three controlled tasks, we show that both factors contribute to the ef- fectiveness of explanations. We further study how to form maximally effective sets of expla- nations for solving a given test query. We find that LLMs can benefit from the complemen- tarity of the explanation set: diverse reasoning skills shown by different exemplars can lead to better performance. Therefore, we propose a maximal marginal relevance-based exemplar selection approach for constructing exemplar sets that are both relevant as well as comple- mentary, which successfully improves the in- context learning performance across three real- world tasks on multiple LLMs.

Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low semantic coverage, hallucination, and logical inconsistency. We propose MURMUR a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning. MURMUR is a best-first search method that generates reasoning paths using: (1) neural and symbolic modules with specific linguistic and logical skills, (2) a grammar whose production rules define valid compositions of modules, and (3) value functions that assess the quality of each reasoning step. We conduct experiments on two diverse data-to-text generation tasks like WebNLG and LogicNLG. The tasks differ in their data representations (graphs and tables) and span multiple linguistic and logical skills. MURMUR obtains significant improvements over recent few-shot baselines like direct prompting and chain-of-thought prompting, while also achieving comparable performance to fine-tuned GPT-2 on out-of-domain data. Moreover, human evaluation shows that MURMUR generates highly faithful and correct reasoning paths that lead to 26% more logically consistent summaries on LogicNLG, compared to direct prompting.

Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcoming CF. Some work has also been done on KT when the tasks are similar. To our knowledge, only one method has been proposed to learn a sequence of mixed tasks. However, these techniques still suffer from CF and/or limited KT. This paper proposes a new CL method to achieve both. It overcomes CF by isolating the knowledge of each task via discovering a sub-network for it. A soft-masking mechanism is also proposed to preserve the previous knowledge and to enable the new task to leverage the past knowledge to achieve KT. Experiments using classification, generation, information extraction, and their mixture (i.e., heterogeneous tasks) show that the proposed method consistently outperforms strong baselines.

Given a prefix (context), open-ended generation aims to decode texts that are coherent, which do not abruptly drift from previous topics, and informative, which do not suffer from undesired repetitions. In this paper, we propose Look-back, an improved decoding algorithm that leverages the Kullback–Leibler divergence to track the distribution distance between current and historical decoding steps. Thus Look-back can automatically predict potential repetitive phrase and topic drift, and remove tokens that may cause the failure modes, restricting the next token probability distribution within a plausible distance to the history. We perform decoding experiments on document continuation and story generation, and demonstrate that Look-back is able to generate more fluent and coherent text, outperforming other strong decoding methods significantly in both automatic and human evaluations.

Model-based evaluation metrics (e.g., CLIPScore and GPTScore) have demonstrated decent correlations with human judgments in various language generation tasks. However, their impact on fairness remains largely unexplored. It is widely recognized that pretrained models can inadvertently encode societal biases, thus employing these models for evaluation purposes may inadvertently perpetuate and amplify biases. For example, an evaluation metric may favor the caption “a woman is calculating an account book” over “a man is calculating an account book,” even if the image only shows male accountants. In this paper, we conduct a systematic study of gender biases in model-based automatic evaluation metrics for image captioning tasks. We start by curating a dataset comprising profession, activity, and object concepts associated with stereotypical gender associations. Then, we demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations, as well as the propagation of biases to generation models through reinforcement learning. Finally, we present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments. Our dataset and framework lay the foundation for understanding the potential harm of model-based evaluation metrics, and facilitate future works to develop more inclusive evaluation metrics.

Extensive work has shown that the performance and interpretability of commonsense reasoning can be improved via knowledge-augmented reasoning methods, where the knowledge that underpins the reasoning process is explicitly verbalized and utilized. However, existing implementations, including “chain-of-thought” and its variants, fall short in capturing the *introspective* nature of knowledge required in commonsense reasoning, and in accounting for the mutual adaptation between the generation and utilization of knowledge. We propose a novel method to develop an introspective commonsense reasoner, **Crystal**. To tackle commonsense problems, it first introspects for knowledge statements related to the given question, and subsequently makes an informed prediction that is grounded in the previously introspected knowledge. The knowledge introspection and knowledge-grounded reasoning modes of the model are tuned via reinforcement learning to mutually adapt, where the reward derives from the feedback given by the model itself. Experiments show that Crystal significantly outperforms both the standard supervised finetuning and chain-of-thought distilled methods, and enhances the transparency of the commonsense reasoning process. Our work ultimately validates the feasibility and potential of reinforcing a neural model with self-feedback.

Language models can memorize a considerable amount of factual information during pretraining that can be elicited through prompting or finetuning models on tasks like question answering. In this paper, we discuss approaches to measuring model factual beliefs, updating incorrect factual beliefs in models, and visualizing graphical relationships between factual beliefs. Our main contributions include: (1) new metrics for evaluating belief-updating methods focusing on the logical consistency of beliefs, (2) a training objective for Sequential, Local, and Generalizing updates (SLAG) that improves the performance of existing hypernetwork approaches, and (3) the introduction of the belief graph, a new form of visualization for language models that shows relationships between stored model beliefs. Our experiments suggest that models show only limited consistency between factual beliefs, but update methods can both fix incorrect model beliefs and greatly improve their consistency. Although off-the-shelf optimizers are surprisingly strong belief-updating baselines, our learned optimizers can outperform them in more difficult settings than have been considered in past work.

We conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT) models as a representative of such models. Our study entails finetuning three different sizes of OPT on a carefully curated reasoning corpus, resulting in two sets of finetuned models: OPT-R, finetuned without explanations, and OPT-RE, finetuned with explanations. We then evaluate all models on 57 out-of-domain tasks drawn from the Super-NaturalInstructions benchmark, covering 26 distinct reasoning skills, utilizing three prompting techniques. Through a comprehensive grid of 27 configurations and 6,156 test evaluations, we investigate the dimensions of finetuning, prompting, and scale to understand the role of explanations on different reasoning skills. Our findings reveal that having explanations in the fewshot exemplar has no significant impact on the model’s performance when the model is finetuned, while positively affecting the non-finetuned counterpart. Moreover, we observe a slight yet consistent increase in classification accuracy as we incorporate explanations during prompting and finetuning, respectively. Finally, we offer insights on which reasoning skills benefit the most from incorporating explanations during finetuning and prompting, such as Numerical (+20.4%) and Analogical (+13.9%) reasoning, as well as skills that exhibit negligible or negative effects.

Current language models can generate high-quality text. Are they simply copying text they have seen before, or have they learned generalizable linguistic abstractions? To tease apart these possibilities, we introduce RAVEN, a suite of analyses for assessing the novelty of generated text, focusing on sequential structure (n-grams) and syntactic structure. We apply these analyses to four neural language models trained on English (an LSTM, a Transformer, Transformer-XL, and GPT-2). For local structure—e.g., individual dependencies—text generated with a standard sampling scheme is substantially less novel than our baseline of human-generated text from each model’s test set. For larger-scale structure—e.g., overall sentence structure—model-generated text is as novel or even more novel than the human-generated baseline, but models still sometimes copy substantially, in some cases duplicating passages over 1,000 words long from the training set. We also perform extensive manual analysis, finding evidence that GPT-2 uses both compositional and analogical generalization mechanisms and showing that GPT-2’s novel text is usually well-formed morphologically and syntactically but has reasonably frequent semantic issues (e.g., being self-contradictory).

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained neural language models, substantial amounts of hallucinated content are found during the human evaluation. In this work, we first devised a typology of factual errors to better understand the types of hallucinations generated by current models and conducted human evaluation on popular dialog summarization dataset. We further propose a training strategy that improves the factual consistency and overall quality of summaries via a novel contrastive fine-tuning, called CONFIT. To tackle top factual errors from our annotation, we introduce additional contrastive loss with carefully designed hard negative samples and self-supervised dialogue-specific loss to capture the key information between speakers. We show that our model significantly reduces all kinds of factual errors on both SAMSum dialogue summarization and AMI meeting summarization. On both datasets, we achieve significant improvements over state-of-the-art baselines using both automatic metrics, ROUGE and BARTScore, and human evaluation.

Current pre-trained models applied for summarization are prone to factual inconsistencies that misrepresent the source text. Evaluating the factual consistency of summaries is thus necessary to develop better models. However, the human evaluation setup for evaluating factual consistency has not been standardized. To determine the factors that affect the reliability of the human evaluation, we crowdsource evaluations for factual consistency across state-of-the-art models on two news summarization datasets using the rating-based Likert Scale and ranking-based Best-Worst Scaling. Our analysis reveals that the ranking-based Best-Worst Scaling offers a more reliable measure of summary quality across datasets and that the reliability of Likert ratings highly depends on the target dataset and the evaluation design. To improve crowdsourcing reliability, we extend the scale of the Likert rating and present a scoring algorithm for Best-Worst Scaling that we call value learning. Our crowdsourcing guidelines will be publicly available to facilitate future work on factual consistency in summarization.

Hate speech detection is complex; it relies on commonsense reasoning, knowledge of stereotypes, and an understanding of social nuance that differs from one culture to the next. It is also difficult to collect a large-scale hate speech annotated dataset. In this work, we frame this problem as a few-shot learning task, and show significant gains with decomposing the task into its “constituent” parts. In addition, we see that infusing knowledge from reasoning datasets (e.g. ATOMIC2020) improves the performance even further. Moreover, we observe that the trained models generalize to out-of-distribution datasets, showing the superiority of task decomposition and knowledge infusion compared to previously used methods. Concretely, our method outperforms the baseline by 17.83% absolute gain in the 16-shot case.

Current efficient fine-tuning methods(e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While showing strong performance on some generation tasks, they don’t generalize across all generation tasks. We show that soft-prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text.We investigate two design choices: First, we apply hierarchical blocking on the prefix parameters to simulate a higher-level discourse structure of human written text. Second, we apply attention sparsity on the prefix parameters at different layers of the network and learn sparse transformations on the softmax-function. We show that structured design of prefix parameters yields more coherent, faithful and relevant generations than the baseline prefix-tuning on all generation tasks.

Abstractive dialogue summarization has long been viewed as an important standalone task in natural language processing, but no previous work has explored the possibility of whether abstractive dialogue summarization can also be used as a means to boost an NLP system’s performance on other important dialogue comprehension tasks. In this paper, we propose a novel type of dialogue summarization task - STRUctured DiaLoguE Summarization (STRUDEL) - that can help pre-trained language models to better understand dialogues and improve their performance on important dialogue comprehension tasks. In contrast to the holistic approach taken by the traditional free-form abstractive summarization task for dialogues, STRUDEL aims to decompose and imitate the hierarchical, systematic and structured mental process that we human beings usually go through when understanding and analyzing dialogues, and thus has the advantage of being more focused, specific and instructive for dialogue comprehension models to learn from. We further introduce a new STRUDEL dialogue comprehension modeling framework that integrates STRUDEL into a dialogue reasoning module over transformer encoder language models to improve their dialogue comprehension ability. In our empirical experiments on two important downstream dialogue comprehension tasks - dialogue question answering and dialogue response prediction - we demonstrate that our STRUDEL dialogue comprehension models can significantly improve the dialogue comprehension performance of transformer encoder language models.

Recent works that revealed the vulnerability of dialogue state tracking (DST) models to distributional shifts have made holistic comparisons on robustness and qualitative analyses increasingly important for understanding their relative performance. We present our findings from standardized and comprehensive DST diagnoses, which have previously been sparse and uncoordinated, using our toolkit, CheckDST, a collection of robustness tests and failure mode analytics. We discover that different classes of DST models have clear strengths and weaknesses, where generation models are more promising for handling language variety while span-based classification models are more robust to unseen entities. Prompted by this discovery, we also compare checkpoints from the same model and find that the standard practice of selecting checkpoints using validation loss/accuracy is prone to overfitting and each model class has distinct patterns of failure. Lastly, we demonstrate how our diagnoses motivate a pre-finetuning procedure with non-dialogue data that offers comprehensive improvements to generation models by alleviating the impact of distributional shifts through transfer learning.

Recent years have brought about an interest in the challenging task of summarizing conversation threads (meetings, online discussions, etc.). Such summaries help analysis of the long text to quickly catch up with the decisions made and thus improve our work or communication efficiency. To spur research in thread summarization, we have developed an abstractive Email Thread Summarization (EmailSum) dataset, which contains human-annotated short (<30 words) and long (<100 words) summaries of 2,549 email threads (each containing 3 to 10 emails) over a wide variety of topics. We perform a comprehensive empirical study to explore different summarization techniques (including extractive and abstractive methods, single-document and hierarchical models, as well as transfer and semisupervised learning) and conduct human evaluations on both short and long summary generation tasks. Our results reveal the key challenges of current abstractive summarization models in this task, such as understanding the sender’s intent and identifying the roles of sender and receiver. Furthermore, we find that widely used automatic evaluation metrics (ROUGE, BERTScore) are weakly correlated with human judgments on this email thread summarization task. Hence, we emphasize the importance of human evaluation and the development of better metrics by the community.

Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We test these methods on translating from English into morphologically rich languages, Turkish and Inuktitut, and consider both automatic metrics and human evaluations. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset. In sum, structural encoding methods make Transformers more sample-efficient, enabling them to perform better from smaller amounts of data.

Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of information scattered across the long document, and (2) composing a cohesive text by reconstructing these salient facts into a shorter summary that faithfully reflects the complex relations connecting these facts. In this paper, we adapt TP-Transformer (Schlag et al., 2019), an architecture that enriches the original Transformer (Vaswani et al., 2017) with the explicitly compositional Tensor Product Representation (TPR), for the task of abstractive summarization. The key feature of our model is a structural bias that we introduce by encoding two separate representations for each token to represent the syntactic structure (with role vectors) and semantic content (with filler vectors) separately. The model then binds the role and filler vectors into the TPR as the layer output. We argue that the structured intermediate representations enable the model to take better control of the contents (salient facts) and structures (the syntax that connects the facts) when generating the summary. Empirically, we show that our TP-Transformer outperforms the Transformer and the original TP-Transformer significantly on several abstractive summarization datasets based on both automatic and human evaluations. On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and the performance gain by information specificity of the role vectors and improved syntactic interpretability in the TPR layer outputs.(Code and models are available at https://github.com/jiangycTarheel/TPT-Summ)

Meetings are a key component of human collaboration. As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed. However, it is hard to create a single short summary that covers all the content of a long meeting involving multiple people and topics. In order to satisfy the needs of different types of users, we define a new query-based multi-domain meeting summarization task, where models have to select and summarize relevant spans of meetings in response to a query, and we introduce QMSum, a new benchmark for this task. QMSum consists of 1,808 query-summary pairs over 232 meetings in multiple domains. Besides, we investigate a locate-then-summarize method and evaluate a set of strong summarization baselines on the task. Experimental results and manual analysis reveal that QMSum presents significant challenges in long meeting summarization for future research. Dataset is available at https://github.com/Yale-LILY/QMSum.

Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents. Such a model is useful in generating clarifying options. However, a naive model trained only using the targeted (‘positive’) document set may generate too generic questions that cover a larger scope than delineated by the document set. To address this challenge, we introduce the contrastive learning strategy where given ‘positive’ and ‘negative’ sets of documents, we generate a question that is closely related to the ‘positive’ set but is far away from the ‘negative’ set. This setting allows generated questions to be more specific and related to the target document set. To generate such specific questions, we propose Multi-Source Coordinated Question Generator (MSCQG), a novel framework that includes a supervised learning (SL) stage and a reinforcement learning (RL) stage. In the SL stage, a single-document question generator is trained. In the RL stage, a coordinator model is trained to find optimal attention weights to align multiple single-document generators, by optimizing a reward designed to promote specificity of generated questions. We also develop an effective auxiliary objective, named Set-induced Contrastive Regularization (SCR) that improves the coordinator’s contrastive learning during the RL stage. We show that our model significantly outperforms several strong baselines, as measured by automatic metrics and human evaluation. The source repository is publicly available at ‘www.github.com/woonsangcho/contrast_qgen’.

Redundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step. Previous work shows the efficacy of jointly scoring and selecting sentences with neural sequence generation models. It is, however, not well-understood if the gain is due to better encoding techniques or better redundancy reduction approaches. Similarly, the contribution of salience versus diversity components on the created summary is not studied well. Building on the state-of-the-art encoding methods for summarization, we present two adaptive learning models: AREDSUM-SEQ that jointly considers salience and novelty during sentence selection; and a two-step AREDSUM-CTX that scores salience first, then learns to balance salience and redundancy, enabling the measurement of the impact of each aspect. Empirical results on CNN/DailyMail and NYT50 datasets show that by modeling diversity explicitly in a separate step, AREDSUM-CTX achieves significantly better performance than AREDSUM-SEQ as well as state-of-the-art extractive summarization baselines.

We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary. Our work addresses current limitations of models for abstractive summarization that often hallucinate information or generate summaries with coherence issues. To generate abstractive summaries with factual consistency and narrative flow, we propose Cooperative Generator-Discriminator Networks (Co-opNet), a novel transformer-based framework where the generator works with a discriminator architecture to compose coherent long-form summaries. We explore four different discriminator objectives which each capture a different aspect of coherence, including whether salient spans of generated abstracts are hallucinated or appear in the input context, and the likelihood of sentence adjacency in generated abstracts. We measure the ability of Co-opNet to learn these objectives with arXiv scientific papers, using the abstracts as a proxy for gold long-form scientific article summaries. Empirical results from automatic and human evaluations demonstrate that Co-opNet learns to summarize with considerably improved global coherence compared to competitive baselines.

Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series. However, real-world dialogues pose a great challenge to current summarization models, as the dialogue length typically exceeds the input limits imposed by recent transformer-based pre-trained models, and the interactive nature of dialogues makes relevant information more context-dependent and sparsely distributed than news articles. In this work, we perform a comprehensive study on long dialogue summarization by investigating three strategies to deal with the lengthy input problem and locate relevant information: (1) extended transformer models such as Longformer, (2) retrieve-then-summarize pipeline models with several dialogue utterance retrieval methods, and (3) hierarchical dialogue encoding models such as HMNet. Our experimental results on three long dialogue datasets (QMSum, MediaSum, SummScreen) show that the retrieve-then-summarize pipeline models yield the best performance. We also demonstrate that the summary quality can be further improved with a stronger retrieval model and pretraining on proper external summarization datasets.

Many high-level procedural tasks can be decomposed into sequences of instructions that vary in their order and choice of tools. In the cooking domain, the web offers many, partially-overlapping, text and video recipes (i.e. procedures) that describe how to make the same dish (i.e. high-level task). Aligning instructions for the same dish across different sources can yield descriptive visual explanations that are far richer semantically than conventional textual instructions, providing commonsense insight into how real-world procedures are structured. Learning to align these different instruction sets is challenging because: a) different recipes vary in their order of instructions and use of ingredients; and b) video instructions can be noisy and tend to contain far more information than text instructions. To address these challenges, we use an unsupervised alignment algorithm that learns pairwise alignments between instructions of different recipes for the same dish. We then use a graph algorithm to derive a joint alignment between multiple text and multiple video recipes for the same dish. We release the Microsoft Research Multimodal Aligned Recipe Corpus containing ~150K pairwise alignments between recipes across 4262 dishes with rich commonsense information.

We describe Artemis (Annotation methodology for Rich, Tractable, Extractive, Multi-domain, Indicative Summarization), a novel hierarchical annotation process that produces indicative summaries for documents from multiple domains. Current summarization evaluation datasets are single-domain and focused on a few domains for which naturally occurring summaries can be easily found, such as news and scientific articles. These are not sufficient for training and evaluation of summarization models for use in document management and information retrieval systems, which need to deal with documents from multiple domains. Compared to other annotation methods such as Relative Utility and Pyramid, Artemis is more tractable because judges don’t need to look at all the sentences in a document when making an importance judgment for one of the sentences, while providing similarly rich sentence importance annotations. We describe the annotation process in detail and compare it with other similar evaluation systems. We also present analysis and experimental results over a sample set of 532 annotated documents.

Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent RMM where robots need to both ask and answer questions.

We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline. This task is challenging as the input only provides a rough sketch of the plot, and thus, models need to generate a story by interweaving the key points provided in the outline. This requires the model to keep track of the dynamic states of the latent plot, conditioning on the input outline while generating the full story. We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative. Comprehensive experiments over three fiction and non-fiction datasets demonstrate that large-scale language models, such as GPT-2 and Grover, despite their impressive generation performance, are not sufficient in generating coherent narratives for the given outline, and dynamic plot state tracking is important for composing narratives with tighter, more consistent plots.

Existing language models excel at writing from scratch, but many real-world scenarios require rewriting an existing document to fit a set of constraints. Although sentence-level rewriting has been fairly well-studied, little work has addressed the challenge of rewriting an entire document coherently. In this work, we introduce the task of document-level targeted content transfer and address it in the recipe domain, with a recipe as the document and a dietary restriction (such as vegan or dairy-free) as the targeted constraint. We propose a novel model for this task based on the generative pre-trained language model (GPT-2) and train on a large number of roughly-aligned recipe pairs. Both automatic and human evaluations show that our model out-performs existing methods by generating coherent and diverse rewrites that obey the constraint while remaining close to the original document. Finally, we analyze our model’s rewrites to assess progress toward the goal of making language generation more attuned to constraints that are substantive rather than stylistic.

Neural Language Generation (NLG) – using neural network models to generate coherent text – is among the most promising methods for automated text creation. Recent years have seen a paradigm shift in neural text generation, caused by the advances in deep contextual language modeling (e.g., LSTMs, GPT, GPT2) and transfer learning (e.g., ELMo, BERT). While these tools have dramatically improved the state of NLG, particularly for low resources tasks, state-of-the-art NLG models still face many challenges: a lack of diversity in generated text, commonsense violations in depicted situations, difficulties in making use of factual information, and difficulties in designing reliable evaluation metrics. In this tutorial, we will present an overview of the current state-of-the-art in neural network architectures, and how they shaped recent research directions in text generation. We will discuss how and why these models succeed/fail at generating coherent text, and provide insights on several applications.

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise to a large memory footprint and slow retrieval speed, which hinders their applicability to low-resource (memory and computation) platforms, such as mobile devices. In this paper, we propose four different strategies to transform continuous and generic sentence embeddings into a binarized form, while preserving their rich semantic information. The introduced methods are evaluated across a wide range of downstream tasks, where the binarized sentence embeddings are demonstrated to degrade performance by only about 2% relative to their continuous counterparts, while reducing the storage requirement by over 98%. Moreover, with the learned binary representations, the semantic relatedness of two sentences can be evaluated by simply calculating their Hamming distance, which is more computational efficient compared with the inner product operation between continuous embeddings. Detailed analysis and case study further validate the effectiveness of proposed methods.

Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables. However, previous works typically focus on synthesizing relatively short sentences (up to 20 words), and the posterior collapse issue has been widely identified in text-VAEs. In this paper, we propose to leverage several multi-level structures to learn a VAE model for generating long, and coherent text. In particular, a hierarchy of stochastic layers between the encoder and decoder networks is employed to abstract more informative and semantic-rich latent codes. Besides, we utilize a multi-level decoder structure to capture the coherent long-term structure inherent in long-form texts, by generating intermediate sentence representations as high-level plan vectors. Extensive experimental results demonstrate that the proposed multi-level VAE model produces more coherent and less repetitive long text compared to baselines as well as can mitigate the posterior-collapse issue.

For evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming. The most common automatic metrics, like BLEU and ROUGE, depend on exact word matching, an inflexible approach for measuring semantic similarity. We introduce methods based on sentence mover’s similarity; our automatic metrics evaluate text in a continuous space using word and sentence embeddings. We find that sentence-based metrics correlate with human judgments significantly better than ROUGE, both on machine-generated summaries (average length of 3.4 sentences) and human-authored essays (average length of 7.5). We also show that sentence mover’s similarity can be used as a reward when learning a generation model via reinforcement learning; we present both automatic and human evaluations of summaries learned in this way, finding that our approach outperforms ROUGE.

We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only store loosely structured open-text descriptions of knowledge. We posit that an important step toward automatic commonsense completion is the development of generative models of commonsense knowledge, and propose COMmonsEnse Transformers (COMET) that learn to generate rich and diverse commonsense descriptions in natural language. Despite the challenges of commonsense modeling, our investigation reveals promising results when implicit knowledge from deep pre-trained language models is transferred to generate explicit knowledge in commonsense knowledge graphs. Empirical results demonstrate that COMET is able to generate novel knowledge that humans rate as high quality, with up to 77.5% (ATOMIC) and 91.7% (ConceptNet) precision at top 1, which approaches human performance for these resources. Our findings suggest that using generative commonsense models for automatic commonsense KB completion could soon be a plausible alternative to extractive methods.

Variational autoencoders (VAE) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. VAE objective consists of two terms, the KL regularization term and the reconstruction term, balanced by a weighting hyper-parameter 𝛽. One notorious training difficulty is that the KL term tends to vanish. In this paper we study different scheduling schemes for 𝛽, and show that KL vanishing is caused by the lack of good latent codes in training decoder at the beginning of optimization. To remedy the issue, we propose a cyclical annealing schedule, which simply repeats the process of increasing 𝛽 multiple times. This new procedure allows us to learn more meaningful latent codes progressively by leveraging the results of previous learning cycles as warm re-restart. The effectiveness of cyclical annealing schedule is validated on a broad range of NLP tasks, including language modeling, dialog response generation and semi-supervised text classification.

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report two simple but highly effective methods to address these challenges and lead to a new state-of-the-art performance. First, we adapt large-scale pretrained language models to learn text representations that generalize better to previously unseen instructions. Second, we propose a stochastic sampling scheme to reduce the considerable gap between the expert actions in training and sampled actions in test, so that the agent can learn to correct its own mistakes during long sequential action decoding. Combining the two techniques, we achieve a new state of the art on the Room-to-Room benchmark with 6% absolute gain over the previous best result (47% -> 53%) on the Success Rate weighted by Path Length metric.

In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.

We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance of the entire system is not robust to the accumulated errors. This paper presents a novel end-to-end learning framework for task-completion dialogue systems to tackle such issues. Our neural dialogue system can directly interact with a structured database to assist users in accessing information and accomplishing certain tasks. The reinforcement learning based dialogue manager offers robust capabilities to handle noises caused by other components of the dialogue system. Our experiments in a movie-ticket booking domain show that our end-to-end system not only outperforms modularized dialogue system baselines for both objective and subjective evaluation, but also is robust to noises as demonstrated by several systematic experiments with different error granularity and rates specific to the language understanding module.

Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical framework of options over Markov Decision Processes (MDPs), and proposing a hierarchical deep reinforcement learning approach to learning a dialogue manager that operates at different temporal scales. The dialogue manager consists of: (1) a top-level dialogue policy that selects among subtasks or options, (2) a low-level dialogue policy that selects primitive actions to complete the subtask given by the top-level policy, and (3) a global state tracker that helps ensure all cross-subtask constraints be satisfied. Experiments on a travel planning task with simulated and real users show that our approach leads to significant improvements over three baselines, two based on handcrafted rules and the other based on flat deep reinforcement learning.

In the past decade, goal-oriented spoken dialogue systems have been the most prominent component in today's virtual personal assistants. The classic dialogue systems have rather complex and/or modular pipelines. The advance of deep learning technologies has recently risen the applications of neural models to dialogue modeling. However, how to successfully apply deep learning based approaches to a dialogue system is still challenging. Hence, this tutorial is designed to focus on an overview of the dialogue system development while describing most recent research for building dialogue systems and summarizing the challenges, in order to allow researchers to study the potential improvements of the state-of-the-art dialogue systems. The tutorial material is available at http://deepdialogue.miulab.tw.