Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Publications
Sort By
1 - 15 of 1076 publications
Preview abstract
Sequence labeling is a core task in text understanding for IE/IR systems. Text generation models have increasingly become the go-to solution for such tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect -- of vital practical importance -- has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder's output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach -- which leverages statistics from top-k predictions by a beam search -- significantly reduces calibration errors of the predictions of a generative sequence labeling model.
View details
Conformal Language Modeling
Victor Quach
Adam Fisch
Adam Yala
Jae Ho Sohn
Tommi Jaakkola
Regina Barzilay
ICLR (2024) (to appear)
Preview abstract
In this paper, we propose a novel approach to conformal prediction (CP) that is adapted to generative, large language models (LLMs). Conformal prediction is a popular technique for deriving prediction sets from machine learning models that have rigorous, statistical performance guarantees. We extend conformal techniques to a broad class of language models that sample from a conditional distribution over the combinatorial, unbounded space of possible text outputs, given some input prompt. Specifically, we translate the process of constructing prediction sets into calibrating a \emph{stopping rule}, under which we draw diverse samples from our model until we are confident that the growing set of candidate answers includes at least one high-quality response. At the same time, we calibrate a \emph{rejection rule} to selectively discard low-quality or redundant responses to reduce sample noise. Under minimal assumptions, we theoretically prove that our resulting output sets contain at least one high-quality answer with some desired probability that a user can set (such as $90\%$), while still remaining empirically precise on average. Furthermore, within this set of sampled candidate answers, we show that we can also accurately identify subsets of individual components (e.g., phrases or sentences) that are each independently correct (e.g., that are not ``hallucinations'')---again, with provably high probability. We demonstrate the effectiveness of our approach on multiple types of large language models applied to tasks in open-domain question answering, text summarization, and radiology report generation.
View details
Demystifying Embedding Spaces using Large Language Models
Jihwan Jeong
Lior Shani
Martin Mladenov
The Twelfth International Conference on Learning Representations (2024)
Preview abstract
Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream tasks make use of these compressed representations, meaningful interpretation usually requires visualization using dimensionality reduction or specialized machine learning interpretability methods. This paper addresses the challenge of making such embeddings more interpretable and broadly useful, by employing large language models (LLMs) to directly interact with embeddings -- transforming abstract vectors into understandable narratives. By injecting embeddings into LLMs, we enable querying and exploration of complex embedding data. We demonstrate our approach on a variety of diverse tasks, including: enhancing concept activation vectors (CAVs), communicating novel embedded entities, and decoding user preferences in recommender systems. Our work couples the immense information potential of embeddings with the interpretative power of LLMs.
View details
Preview abstract
As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a multilingual LLM affects instruction-following across languages from the pre-training corpus. We first show that many languages transfer some instruction-following capabilities to other languages from even monolingual tuning. Furthermore, we find that only 40 multilingual examples integrated in an English tuning set substantially improve multilingual instruction-following, both in seen and unseen languages during tuning. In general, we observe that models tuned on multilingual mixtures exhibit comparable or superior performance in multiple languages compared to monolingually tuned models, despite training on 10x fewer examples in those languages. Finally, we find that diversifying the instruction tuning set with even just 2-4 languages significantly improves cross-lingual generalization. Our results suggest that building massively multilingual instruction-tuned models can be done with only a very small set of multilingual instruction-responses.
View details
Preview abstract
Knowledge-grounded dialogue generation is a challenging task because it requires satisfying two fundamental yet often competing constraints: being responsive in a manner that is specific to what the conversation partner has said while also being attributable to an underlying source document. In this work, we bring this trade-off between these two objectives (specificity and attribution) to light and ask the question: Can explicit content planning before the response generation help the model to address this challenge? To answer this question, we design a framework called PLEDGE, which allows us to experiment with various plan variables explored in prior work, supporting both metric-agnostic and metric-aware approaches. While content planning shows promise, our results on whether it can actually help to navigate this trade-off are mixed -- planning mechanisms that are metric-aware (use automatic metrics during training) are better at automatic evaluations but underperform in human judgment compared to metric-agnostic mechanisms. We discuss how this may be caused by over-fitting to automatic metrics and the need for future work to better calibrate these metrics towards human judgment. We hope the observations from our analysis will inform future work that aims to apply content planning in this context.
View details
Learning to Rewrite Prompts for Personalized Text Generation
Qiaozhu Mei
Proceedings of the ACM Web Conference 2024
Preview abstract
Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the LLMs to generate personalized text. We consider a typical scenario in which the large language model, which generates personalized output, is frozen and can only be accessed through APIs. Under this constraint, all one can do is to improve the input text (i.e., text prompts) sent to the LLM, a procedure that is usually done manually. In this paper, we propose a novel method to automatically revise prompts for personalized text generation. The proposed method takes the initial prompts generated by a state-of-the-art, multistage framework for personalized generation and rewrites a few critical components that summarize and synthesize the personal context. The prompt rewriter employs a training paradigm that chains together supervised learning (SL) and reinforcement learning (RL), where SL reduces the search space of RL and RL facilitates end-to-end training of the rewriter. Using datasets from three representative domains, we demonstrate that the rewritten prompts outperform both the original prompts and the prompts optimized via supervised learning or reinforcement learning alone. In-depth analysis of the rewritten prompts shows that they are not only human readable, but also able to guide manual revision of prompts when there is limited resource to employ reinforcement learning to train the prompt rewriter, or when it is costly to deploy an automatic prompt rewriter for inference.
View details
Batch Calibration: Rethinking Calibration For In-Context Learning And Prompt Engineering
Han Zhou
Lev Proleev
International Conference on Learning Representations (ICLR) (2024)
Preview abstract
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias factors in the prompt, including but not limited to the formatting, the choice verbalizers, and the ICL examples. To address this problem that results in unexpected performance degradation, calibration methods have been developed to mitigate the effects of these biases while recovering LLM performance. In this work, we first conduct a systematic analysis of the existing calibration methods, where we both provide a unified view and reveal the failure cases. Inspired by these analyses, we propose Batch Calibration (BC), a simple yet intuitive method that controls the contextual bias from the batched input, unifies various prior approaches, and effectively addresses the aforementioned issues. BC is zero-shot, inference-only, and incurs negligible additional costs. In the few-shot setup, we further extend BC to allow it to learn the contextual bias from labeled data. We validate the effectiveness of BC with PaLM 2-(S, M, L) and CLIP models and demonstrate state-of-the-art performance over previous calibration baselines across more than 10 natural language understanding and image classification tasks.
View details
SEMQA: Semi-Extractive Multi-Source Question Answering
Haitian Sun
NAACL (2024) (to appear)
Preview abstract
Recently proposed long-form question answering (QA) systems, supported by large language models (LLMs), have shown promising capabilities. Yet, attributing and verifying their generated abstractive answers can be difficult, and automatically evaluating their accuracy remains an ongoing challenge.
In this paper, we introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion. Specifically, Semi-extractive Multi-source QA (SEMQA) requires models to output a comprehensive answer while mixing between factual quoted spans---copied verbatim from given input sources---and non-factual free-text connectors that glue these spans together into a single cohesive passage. This setting bridges the gap between the outputs of well-grounded but constrained extractive QA systems and more fluent but harder to attribute fully abstractive answers. Particularly, it enables a new mode for language models that leverages their advanced language generation capabilities, while also producing fine in-line attributions by-design that are easy to verify, interpret, and evaluate. To study this task, we create the first dataset of this kind with human-written semi-extractive answers to natural and generated questions, and define text-based evaluation metrics. Experimenting with several LLMs in various settings, we find this task to be surprisingly challenging, demonstrating the importance of our work for developing and studying such consolidation capabilities.
View details
Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns
Ariel Goldstein
Avigail Grinstein-Dabush
Haocheng Wang
Zhuoqiao Hong
Bobbi Aubrey
Samuel A. Nastase
Zaid Zada
Eric Ham
Harshvardhan Gazula
Eliav Buchnik
Werner Doyle
Sasha Devore
Patricia Dugan
Roi Reichart
Daniel Friedman
Orrin Devinsky
Adeen Flinker
Uri Hasson
Nature Communications (2024)
Preview abstract
Contextual embeddings, derived from deep language models (DLMs), provide
a continuous vectorial representation of language. This embedding space
differs fundamentally from the symbolic representations posited by traditional
psycholinguistics. We hypothesize that language areas in the human brain,
similar to DLMs, rely on a continuous embedding space to represent language.
To test this hypothesis, we densely record the neural activity patterns in the
inferior frontal gyrus (IFG) of three participants using dense intracranial arrays
while they listened to a 30-minute podcast. From these fine-grained spatiotemporal neural recordings, we derive a continuous vectorial representation
for each word (i.e., a brain embedding) in each patient. We demonstrate that
brain embeddings in the IFG and the DLM contextual embedding space have
common geometric patterns using stringent zero-shot mapping. The common
geometric patterns allow us to predict the brain embedding of a given left-out
word in IFG based solely on its geometrical relationship to other nonoverlapping words in the podcast. Furthermore, we show that contextual
embeddings better capture the geometry of IFG embeddings than static word
embeddings. The continuous brain embedding space exposes a vector-based
neural code for natural language processing in the human brain.
View details
Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation
Lion Jones
Haruko Ishikawa
Transactions of the Association for Computational Linguistics, vol. 11 (2023), 85–101
Preview abstract
If one sees the place name Houston Mercer Dog Run in New York, how does one know how to pronounce it? Assuming one knows that Houston in New York is pronounced ˈhaʊstən and not like the Texas city (ˈhjuːstən), then one can probably guess that ˈhaʊstən is also used in the name of the dog park. We present a novel architecture that learns to use the pronunciations of neighboring names in order to guess the pronunciation of a given target feature. Applied to Japanese place names, we demonstrate the utility of the model to finding and proposing corrections for errors in Google Maps.
To demonstrate the utility of this approach to structurally similar problems, we also report on an application to a totally different task: Cognate reflex prediction in comparative historical linguistics. A version of the code has been open-sourced.
View details
Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation
Fantine Huot
Reinald Kim Amplayo
Mirella Lapata
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations (2023)
Preview abstract
While conditional generation models can now generate natural language well enough to create fluent text, it is still difficult to control the generation process, leading to irrelevant, repetitive, and hallucinated content. Recent work shows that planning can be a useful intermediate step to render conditional generation less opaque and more grounded. We present a web browser-based demonstration for query-focused summarization that uses a sequence of question-answer pairs, as a blueprint plan for guiding text generation (i.e., what to say and in what order). We illustrate how users may interact with the generated text and associated plan visualizations, e.g., by editing and modifying the blueprint in order to improve or control the generated output.
View details
MoQA: Benchmarking Multi-Type Open-Domain Question Answering
Howard Yen
Tianyu Gao
Danqi Chen
Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, Association for Computational Linguistics (2023), 8–29
Preview abstract
Existing open-domain question answering research mainly focuses on questions that can be answered in a few words.
However, information-seeking questions often require different formats of answers depending on the nature of questions, e.g., ``Why is there a maple leaf on the Canadian flag?''
In this paper, we present a new task, MOQA, which requires building QA models that can provide short, medium, long, and yes/no answers to open-domain questions simultaneously.
We expand the Natural Questions dataset into the open-domain setting by keeping all types of questions and show that existing systems cannot generalize to these new types.
We adapt state-of-the-art open-domain QA models---based on retriever-reader and phrase retrieval models---to tackle this task.
Results and analyses of our multi-type QA models reveal the unique challenges of the task, calling for versatile QA models in the future.
View details
Preview abstract
Naturally-occurring information-seeking questions often contain questionable assumptions---assumptions that are false or unverifiable. Questions containing questionable assumptions are challenging because they require a distinct answer strategy that deviates from typical answers to information-seeking questions. For instance, the question "When did Marie Curie discover Uranium?" cannot be answered as a typical "when" question without addressing the false assumption "Marie Curie discovered Uranium". In this work, we propose (QA)$^2$ (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally-occurring search engine queries that may or may not contain questionable assumptions. To be successful on (QA)$^2$, systems must be able to detect questionable assumptions and also be able to produce adequate responses for both typical information-seeking questions and ones with questionable assumptions. Through human rater acceptability on abstractive QA with (QA)$^2$ questions, we find that current models do struggle with handling questionable assumptions, leaving substantial headroom for progress.
View details
Preview abstract
Formulating selective information needs results in queries that implicitly specify set operations, such as intersection, union, and difference. For instance, one might search for "shorebirds that are not sandpipers" or "science-fiction films shot in England". To study the ability of retrieval systems to meet such information needs, we construct QUEST, a dataset of 3357 natural language queries with implicit set operations, that map to a set of entities corresponding to Wikipedia documents. The dataset challenges models to match multiple constraints mentioned in queries with corresponding evidence in documents and correctly perform various set operations. The dataset is constructed semi-automatically using Wikipedia category names. Queries are automatically composed from individual categories, then paraphrased and further validated for naturalness and fluency by crowdworkers. Crowdworkers also assess the relevance of entities based on their documents and highlight attribution of query constraints to spans of document text. We analyze several modern retrieval systems, finding that they often struggle on such queries. Queries involving negation and conjunction are particularly challenging and systems are further challenged with combinations of these operations.
View details
Joint Adaptive Representations for Image-Language Learning
Transformers for Vision (T4V) Workshop at the Conference on Computer Vision and Pattern Recognition (CVPR) (2023)
Preview abstract
Image-language transformer models have achieved tremendous success, but they come at high computational costs. We here propose a joint adaptive image-language representation learning, which adaptively and iteratively fuses the multi-modal features. This consistently reduces the model cost and size, allows the model to scale without a large increase in FLOPs or memory, and outperforms bigger and much more expensive models. With only 40M training examples and with 39 GFLOPs our model outperforms many times larger models, some reaching 800 GFLOPs.
View details
