Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user’s intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model (LLM) can amplify an expert’s guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorporated into clustering: before clustering (improving input features), during clustering (by providing constraints to the clusterer), and after clustering (using LLMs post-correction). We find that incorporating LLMs in the first two stages routinely provides significant improvements in cluster quality, and that LLMs enable a user to make trade-offs between cost and accuracy to produce desired clusters. We release our code and LLM prompts for the public to use.1

One widely cited barrier to the adoption of LLMs as proxies for humans in subjective tasks is their sensitivity to prompt wording—but interestingly, humans also display sensitivities to instruction changes in the form of response biases. We investigate the extent to which LLMs reflect human response biases, if at all. We look to survey design, where human response biases caused by changes in the wordings of “prompts” have been extensively explored in social psychology literature. Drawing from these works, we design a dataset and framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior, particularly in models that have undergone RLHF. Furthermore, even if a model shows a significant change in the same direction as humans, we find that they are sensitive to perturbations that do not elicit significant changes in humans. These results highlight the pitfalls of using LLMs as human proxies, and underscore the need for finer-grained characterizations of model behavior.1

Despite recent advances in large language models, building dependable and deployable NLP models typically requires abundant, high-quality training data. However, task-specific data is not available for many use cases, and manually curating task-specific data is labor-intensive. Recent work has studied prompt-driven synthetic data generation using large language models, but these generated datasets tend to lack complexity and diversity. To address these limitations, we introduce a method, _DataTune_, to make better use of existing, publicly available datasets to improve automatic dataset generation. DataTune performs _dataset transformation_, enabling the repurposing of publicly available datasets into a format that is directly aligned with the specific requirements of target tasks. On a diverse set of language-based tasks from the BIG-Bench benchmark, we find that finetuning language models via DataTune improves over a few-shot prompting baseline by 49% and improves over existing methods that use synthetic or retrieved training data by 34%. We find that dataset transformation significantly increases the diversity and difficulty of generated data on many tasks. We release a Python package and open-source repository to make this method accessible to the community (URL will be added upon acceptance).

For a LLM to be trustworthy, its confidence level should be well-calibrated with its actual performance. While it is now common sense that LLM performances are greatly impacted by prompts, the confidence calibration in prompting LLMs has yet to be thoroughly explored.In this paper, we explore how different prompting strategies influence LLM confidence calibration and how it could be improved. We conduct extensive experiments on six prompting methods in the question-answering context and we observe that, while these methods help improve the expected LLM calibration, they also trigger LLMs to be over-confident when responding to some instances.Inspired by human cognition, we propose Fact-and-Reflection (FaR) prompting, which improves the LLM calibration in two steps. First, FaR elicits the known “facts” that are relevant to the input prompt from the LLM. And then it asks the model to “reflect” over them to generate the final answer.Experiments show that FaR prompting achieves significantly better calibration; it lowers the Expected Calibration Error by 23.5% on our multi-purpose QA tasks. Notably, FaR prompting even elicits the capability of verbally expressing concerns in less confident scenarios, which helps trigger retrieval augmentation for solving these harder instances.

Multimodal Retrieval Augmented Generation (MMRAG) is a powerful approach to question-answering over multimodal documents. A key challenge with evaluating MMRAG is the paucity of high-quality datasets matching the question styles and modalities of interest. In light of this, we propose SMMQG, a synthetic data generation framework. SMMQG leverages interplay between a retriever, large language model (LLM) and large multimodal model (LMM) to generate question and answer pairs directly from multimodal documents, with the questions conforming to specified styles and modalities. We use SMMQG to generate an MMRAG dataset of 1024 questions over Wikipedia documents and evaluate state-of-the-art models using it, revealing insights into model performance that are attainable only through style- and modality-specific evaluation data. Next, we measure the quality of data produced by SMMQG via a human study. We find that the quality of SMMQG-generated synthetic data is on par with the quality of the crowdsourced benchmark MMQA and that downstream evaluation results using both datasets strongly concur.

Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. We conduct human experiments with 80 crowdworkers to compare language models with search engines (information retrieval systems) at facilitating fact-checking. We prompt LLMs to validate a given claim and provide corresponding explanations. Users reading LLM explanations are significantly more efficient than those using search engines while achieving similar accuracy. However, they over-rely on the LLMs when the explanation is wrong. To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information—explain both why the claim is true and false, and then we present both sides of the explanation to users. This contrastive explanation mitigates users’ over-reliance on LLMs, but cannot significantly outperform search engines. Further, showing both search engine results and LLM explanations offers no complementary benefits compared to search engines alone. Taken together, our study highlights that natural language explanations by LLMs may not be a reliable replacement for reading the retrieved passages, especially in high-stakes settings where over-relying on wrong AI explanations could lead to critical consequences.

Modern machine learning relies on datasets to develop and validate research ideas. Given the growth of publicly available data, finding the right dataset to use is increasingly difficult. Any research question imposes explicit and implicit constraints on how well a given dataset will enable researchers to answer this question, such as dataset size, modality, and domain. We operationalize the task of recommending datasets given a short natural language description of a research idea, to help people find relevant datasets for their needs. Dataset recommendation poses unique challenges as an information retrieval problem; datasets are hard to directly index for search and there are no corpora readily available for this task. To facilitate this task, we build the DataFinder Dataset which consists of a larger automatically-constructed training set (17.5K queries) and a smaller expert-annotated evaluation set (392 queries). Using this data, we compare various information retrieval algorithms on our test set and present a superior bi-encoder retriever for text-based dataset recommendation. This system, trained on the DataFinder Dataset, finds more relevant search results than existing third-party dataset search engines. To encourage progress on dataset recommendation, we release our dataset and models to the public.

Current model testing work has mostly focused on creating test cases. Identifying what to test is a step that is largely ignored and poorly supported. We propose Weaver, an interactive tool that supports requirements elicitation for guiding model testing. Weaver uses large language models to generate knowledge bases and recommends concepts from them interactively, allowing testers to elicit requirements for further testing. Weaver provides rich external knowledge to testers and encourages testers to systematically explore diverse concepts beyond their own biases. In a user study, we show that both NLP experts and non-experts identified more, as well as more diverse concepts worth testing when using Weaver. Collectively, they found more than 200 failing test cases for stance detection with zero-shot ChatGPT. Our case studies further show that Weaver can help practitioners test models in real-world settings, where developers define more nuanced application scenarios (e.g., code understanding and transcript summarization) using LLMs.

Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework that enhances content moderation setups with free-text explanations of statements’ implied social biases, and explore its effectiveness through a large-scale crowdsourced user study. We show that indeed, participants substantially benefit from explanations for correctly identifying subtly (non-)toxic content. The quality of explanations is critical: imperfect machine-generated explanations (+2.4% on hard toxic examples) help less compared to expert-written human explanations (+7.2%). Our results showcase the promise of using free-text explanations to encourage more thoughtful toxicity moderation.

The rapid advancement of natural language processing (NLP) research has led to various applications spanning a wide range of domains that require models to interact with humans – e.g., chatbots responding to human inquiries, machine translation systems assisting human translators, designers prompting Large Language Models for co-creation or prototyping AI-infused applications, etc. In these cases, humans interaction is key to the success of NLP applications; any potential misconceptions or differences might lead to error cascades at the subsequent stages. Such interaction involves a lot of design choices around models, e.g. the sensitivity of interfaces, the impact of design choice and evaluation questions, etc. This tutorial aims to provide a systematic and up-to-date overview of key considerations and effective approaches for studying human-NLP model interactions. Our tutorial will focus specifically on the scenario where end users – lay people and domain experts who have access to NLP models but are less familiar with NLP techniques – use or collaborate with deployed models. Throughout the tutorial, we will use five case studies (on classifier-assisted decision making, machine-aided translation, dialog systems, and prompting) to cover three major themes: (1) how to conduct human-in-the-loop usability evaluations to ensure that models are capable of interacting with humans; (2) how to design user interfaces (UIs) and interaction mechanisms that provide end users with easy access to NLP models; (3) how to learn and improve NLP models through the human interactions. We will use best practices from HCI to ground our discussion, and will highlight current challenges and future directions.

Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provide a few examples. However, in other ways, LLMs are a step backward from traditional special-purpose NLP models; they require extensive computational resources for deployment and can be gated behind APIs. In this paper, we propose Prompt2Model, a general-purpose method that takes a natural language task description like the prompts provided to LLMs, and uses it to train a special-purpose model that is conducive to deployment. This is done through a multi-step process of retrieval of existing datasets and pretrained models, dataset generation using LLMs, and supervised fine-tuning on these retrieved and generated datasets. Over three tasks, we demonstrate that given the same few-shot prompt as input, Prompt2Model trains models that outperform the results of a strong LLM, gpt-3.5-turbo, by an average of 20% while being up to 700 times smaller. We also show that this data can be used to obtain reliable performance estimates of model performance, enabling model developers to assess model reliability before deployment. Prompt2Model is available open-source at https://github.com/neulab/prompt2model. Our demo video is posted at youtu.be/LYYQ_EhGd-Q.

We present NewsSense, a novel sensemaking tool and reading interface designed to collect and integrate information from multiple news articles on a central topic. NewsSense provides “reference-free verification,” augmenting a central grounding article of the user’s choice by: (1) linking to related articles from different sources; and (2) providing inline highlights on how specific claims are either supported or contradicted by information from other articles. Using NewsSense, users can seamlessly digest and cross-check multiple information sources without disturbing their natural reading flow. Our pilot study shows that NewsSense has the potential to help users identify key information, verify the credibility of news articles, explore different perspectives, and understand what content is supported, contradicted, or missing.

Natural language generation has witnessed significant advancements due to the training of large language models on vast internet-scale datasets. Despite these advancements, there exists a critical challenge: These models can inadvertently generate content that is toxic, inaccurate, and unhelpful, and existing automatic evaluation metrics often fall short of identifying these shortcomings. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of recent research that has leveraged human feedback to improve natural language generation. First, we introduce a taxonomy distilled from existing research to categorize and organize the varied forms of feedback. Next, we discuss how feedback can be described by its format and objective, and cover the two approaches proposed to use feedback (either for training or decoding): directly using feedback or training feedback models. We also discuss existing datasets for human-feedback data collection, and concerns surrounding feedback collection. Finally, we provide an overview of the nascent field of AI feedback, which uses large language models to make judgments based on a set of principles and minimize the need for human intervention. We also release a website of this survey at feedback-gap-survey.info.

Question answering (QA) is a fundamental means to facilitate assessment and training of narrative comprehension skills for both machines and young children, yet there is scarcity of high-quality QA datasets carefully designed to serve this purpose. In particular, existing datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements. Drawing on the reading education research, we introduce FairytaleQA, a dataset focusing on narrative comprehension of kindergarten to eighth-grade students. Generated by educational experts based on an evidence-based theoretical framework, FairytaleQA consists of 10,580 explicit and implicit questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations. Our dataset is valuable in two folds: First, we ran existing QA models on our dataset and confirmed that this annotation helps assess models’ fine-grained learning skills. Second, the dataset supports question generation (QG) task in the education domain. Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.

Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student’s comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.

Controlled text perturbation is useful for evaluating and improving model generalizability. However, current techniques rely on training a model for every target perturbation, which is expensive and hard to generalize. We present Tailor, a semantically-controlled text generation system. Tailor builds on a pretrained seq2seq model and produces textual outputs conditioned on control codes derived from semantic representations. We craft a set of operations to modify the control codes, which in turn steer generation towards targeted attributes. These operations can be further composed into higher-level ones, allowing for flexible perturbation strategies. We demonstrate the effectiveness of these perturbations in multiple applications. First, we use Tailor to automatically create high-quality contrast sets for four distinct natural language processing (NLP) tasks. These contrast sets contain fewer spurious artifacts and are complementary to manually annotated ones in their lexical diversity. Second, we show that Tailor perturbations can improve model generalization through data augmentation. Perturbing just ∼2% of training data leads to a 5.8-point gain on an NLI challenge set measuring reliance on syntactic heuristics.

Existing self-explaining models typically favor extracting the shortest possible rationales — snippets of an input text “responsible for” corresponding output — to explain the model prediction, with the assumption that shorter rationales are more intuitive to humans. However, this assumption has yet to be validated. Is the shortest rationale indeed the most human-understandable? To answer this question, we design a self-explaining model, LimitedInk, which allows users to extract rationales at any target length. Compared to existing baselines, LimitedInk achieves compatible end-task performance and human-annotated rationale agreement, making it a suitable representation of the recent class of self-explaining models. We use LimitedInk to conduct a user study on the impact of rationale length, where we ask human judges to predict the sentiment label of documents based only on LimitedInk-generated rationales with different lengths. We show rationales that are too short do not help humans predict labels better than randomly masked text, suggesting the need for more careful design of the best human rationales.

While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as paraphrases or word substitutions. We present Polyjuice, a general-purpose counterfactual generator that allows for control over perturbation types and locations, trained by finetuning GPT-2 on multiple datasets of paired sentences. We show that Polyjuice produces diverse sets of realistic counterfactuals, which in turn are useful in various distinct applications: improving training and evaluation on three different tasks (with around 70% less annotation effort than manual generation), augmenting state-of-the-art explanation techniques, and supporting systematic counterfactual error analysis by revealing behaviors easily missed by human experts.

Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.

Though error analysis is crucial to understanding and improving NLP models, the common practice of manual, subjective categorization of a small sample of errors can yield biased and incomplete conclusions. This paper codifies model and task agnostic principles for informative error analysis, and presents Errudite, an interactive tool for better supporting this process. First, error groups should be precisely defined for reproducibility; Errudite supports this with an expressive domain-specific language. Second, to avoid spurious conclusions, a large set of instances should be analyzed, including both positive and negative examples; Errudite enables systematic grouping of relevant instances with filtering queries. Third, hypotheses about the cause of errors should be explicitly tested; Errudite supports this via automated counterfactual rewriting. We validate our approach with a user study, finding that Errudite (1) enables users to perform high quality and reproducible error analyses with less effort, (2) reveals substantial ambiguities in prior published error analyses practices, and (3) enhances the error analysis experience by allowing users to test and revise prior beliefs.