64 citations · 375 across the 45 of their papers we have counts for
48 papers · 1 filter
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation
Fangyuan Xu, Weijia Shi, Eunsol Choi
Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spannin…
Development and Evaluation of Three Chatbots for Postpartum Mood and Anxiety Disorders
Xuewen Yao, Miriam Mikhelson, S. Craig Watkins +3
In collaboration with Postpartum Support International (PSI), a non-profit organization dedicated to supporting caregivers with postpartum mood and anxiety disorders, we developed…
When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants
Anuj Diwan, Eunsol Choi, David Harwath
We present the first unified study of the efficiency of self-attention-based Transformer variants spanning text, speech and vision. We identify input length thresholds (tipping poi…
Propagating Knowledge Updates to LMs Through Distillation
Shankar Padmanabhan, Yasumasa Onoe, Michael J. Q. Zhang +2
Modern language models have the capacity to store and use immense amounts of knowledge about real-world entities, but it remains unclear how to update such knowledge stored in mode…
Concise Answers to Complex Questions: Summarization of Long-form Answers
Abhilash Potluri, Fangyuan Xu, Eunsol Choi
Long-form question answering systems provide rich information by presenting paragraph-level answers, often containing optional background or auxiliary information. While such compr…
A Critical Evaluation of Evaluations for Long-form Question Answering
Fangyuan Xu, Yixiao Song, Mohit Iyyer +1
Long-form question answering (LFQA) enables answering a wide range of questions, but its flexibility poses enormous challenges for evaluation. We perform the first targeted study o…
Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge
Yasumasa Onoe, Michael J. Q. Zhang, Shankar Padmanabhan +2
Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes. Prior work ha…
Textless Speech-to-Speech Translation With Limited Parallel Data
Anuj Diwan, Anirudh Srinivasan, David Harwath +1
Existing speech-to-speech translation (S2ST) models fall into two camps: they either leverage text as an intermediate step or require hundreds of hours of parallel speech data. Bot…
Mitigating Temporal Misalignment by Discarding Outdated Facts
Michael J. Q. Zhang, Eunsol Choi
While large language models are able to retain vast amounts of world knowledge seen during pretraining, such knowledge is prone to going out of date and is nontrivial to update. Fu…
Continually Improving Extractive QA via Human Feedback
Ge Gao, Hung-Ting Chen, Yoav Artzi +1
We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask…
Complex Claim Verification with Evidence Retrieved in the Wild
Jifan Chen, Grace Kim, Aniruddh Sriram +2
Evidence retrieval is a core part of automatic fact-checking. Prior work makes simplifying assumptions in retrieval that depart from real-world use cases: either no access to evide…
DIFFQG: Generating Questions to Summarize Factual Changes
Jeremy R. Cole, Palak Jain, Julian Martin Eisenschlos +3
Identifying the difference between two versions of the same article is useful to update knowledge bases and to understand how articles evolve. Paired texts occur naturally in diver…
Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality
Anuj Diwan, Layne Berry, Eunsol Choi +2
Recent visuolinguistic pre-trained models show promising progress on various end tasks such as image retrieval and video captioning. Yet, they fail miserably on the recently propos…
TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages
Anirudh Srinivasan, Eunsol Choi
We study politeness phenomena in nine typologically diverse languages. Politeness is an important facet of communication and is sometimes argued to be cultural-specific, yet existi…
Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources
Xinyan Velocity Yu, Akari Asai, Trina Chatterjee +2
While the NLP community is generally aware of resource disparities among languages, we lack research that quantifies the extent and types of such disparity. Prior surveys estimatin…
Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence
Hung-Ting Chen, Michael J. Q. Zhang, Eunsol Choi
Question answering models can use rich knowledge sources -- up to one hundred retrieved passages and parametric knowledge in the large-scale language model (LM). Prior work assumes…
MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages
Akari Asai, Shayne Longpre, Jungo Kasai +6
We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typo…
longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks
Venelin Kovatchev, Trina Chatterjee, Venkata S Govindarajan +9
Developing methods to adversarially challenge NLP systems is a promising avenue for improving both model performance and interpretability. Here, we describe the approach of the tea…
Modeling Exemplification in Long-form Question Answering via Retrieval
Shufan Wang, Fangyuan Xu, Laure Thompson +2
Exemplification is a process by which writers explain or clarify a concept by providing an example. While common in all forms of writing, exemplification is particularly useful in…
Entity Cloze By Date: What LMs Know About Unseen Entities
Yasumasa Onoe, Michael J. Q. Zhang, Eunsol Choi +1
Language models (LMs) are typically trained once on a large-scale corpus and used for years without being updated. However, in a dynamic world, new entities constantly arise. We pr…
Generating Literal and Implied Subquestions to Fact-check Complex Claims
Jifan Chen, Aniruddh Sriram, Eunsol Choi +1
Verifying complex political claims is a challenging task, especially when politicians use various tactics to subtly misrepresent the facts. Automatic fact-checking systems fall sho…
How Do We Answer Complex Questions: Discourse Structure of Long-form Answers
Fangyuan Xu, Junyi Jessy Li, Eunsol Choi
Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied…
Simulating Bandit Learning from User Feedback for Extractive Question Answering
Ge Gao, Eunsol Choi, Yoav Artzi
We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze…
SituatedQA: Incorporating Extra-Linguistic Contexts into QA
Michael J. Q. Zhang, Eunsol Choi
Answers to the same question may change depending on the extra-linguistic contexts (when and where the question was asked). To study this challenge, we introduce SituatedQA, an ope…