Eunsol Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Eunsol Choi has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Fangyuan Xu
Department of Computer Science The University of Texas at Austin
4 shared publications - David Harwath
The University of Texas at Austin
3 shared publications - Michael J. Q. Zhang
Department of Computer Science The University of Texas at Austin
3 shared publications - Anuj Diwan
Department of Computer Science Department of Computer Science and Data Science The University of Texas at Austin New York University
2 shared publications - Bhuwan Dhingra
Google research
2 shared publications - Ge Gao
Department of Computer Science and Cornell Tech Department of Computer Science Cornell University ♣ The University of Texas at Austin
2 shared publications
Latest Publications
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Aligning Data with the Goals of an Organization and Its Workers: Designing Data Labeling for Social Service Case Notes
The challenges of data collection in nonprofits for performance and funding reports are well-established in HCI research. Few studies, however, delve into improving the data collection process. Our study proposes ideas to improve data collection by exploring challenges that social workers experience when labeling their case notes. Through collaboration with an organization that provides intensive case management to those experiencing homelessness in the U.S., we conducted interviews with caseworkers and held design sessions where caseworkers, managers, and program analysts examined storyboarded ideas to improve data labeling. Our findings suggest several design ideas on how data labeling practices can be improved: Aligning labeling with caseworker goals, enabling shared control on data label design for a comprehensive portrayal of caseworker contributions, improving the synthesis of qualitative and quantitative data, and making labeling user-friendly. We contribute design implications for data labeling to better support multiple stakeholder goals in social service contexts.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Open AccessAligning Data with the Goals of an Organization and Its Workers: Designing Data Labeling for Social Service Case Notes
The challenges of data collection in nonprofits for performance and funding reports are well-established in HCI research. Few studies, however, delve into improving the data collection process. Our study proposes ideas to improve data collection by exploring challenges that social workers experience when labeling their case notes. Through collaboration with an organization that provides intensive case management to those experiencing homelessness in the U.S., we conducted interviews with caseworkers and held design sessions where caseworkers, managers, and program analysts examined storyboarded ideas to improve data labeling. Our findings suggest several design ideas on how data labeling practices can be improved: Aligning labeling with caseworker goals, enabling shared control on data label design for a comprehensive portrayal of caseworker contributions, improving the synthesis of qualitative and quantitative data, and making labeling user-friendly. We contribute design implications for data labeling to better support multiple stakeholder goals in social service contexts.
- Open Access
Crafting In-context Examples according to LMs' Parametric Knowledge
In-context learning can improve the performances of knowledge-rich tasks such as question answering. In such scenarios, in-context examples trigger a language model (LM) to surface information stored in its parametric knowledge. We study how to better construct in-context example sets, based on whether the model is aware of the in-context examples. We identify 'known' examples, where models can correctly answer from their parametric knowledge, and 'unknown' ones. Our experiments show that prompting with 'unknown' examples decreases the performance, potentially as it encourages hallucination rather than searching for its parametric knowledge. Constructing an in-context example set that presents both known and unknown information performs the best across diverse settings. We perform analysis on three multi-answer question answering datasets, which allows us to further study answer set ordering strategies based on the LM's knowledge of each answer. Together, our study sheds light on how to best construct in-context example sets for knowledge-rich tasks.
Open AccessCrafting In-context Examples according to LMs' Parametric Knowledge
In-context learning can improve the performances of knowledge-rich tasks such as question answering. In such scenarios, in-context examples trigger a language model (LM) to surface information stored in its parametric knowledge. We study how to better construct in-context example sets, based on whether the model is aware of the in-context examples. We identify 'known' examples, where models can correctly answer from their parametric knowledge, and 'unknown' ones. Our experiments show that prompting with 'unknown' examples decreases the performance, potentially as it encourages hallucination rather than searching for its parametric knowledge. Constructing an in-context example set that presents both known and unknown information performs the best across diverse settings. We perform analysis on three multi-answer question answering datasets, which allows us to further study answer set ordering strategies based on the LM's knowledge of each answer. Together, our study sheds light on how to best construct in-context example sets for knowledge-rich tasks.
- Open Access
Mitigating Temporal Misalignment by Discarding Outdated Facts
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. Furthermore, these models are often used under temporal misalignment, tasked with answering questions about the present, despite having only been trained on data collected in the past. To mitigate the effects of temporal misalignment, we propose fact duration prediction: the task of predicting how long a given fact will remain true. In our experiments, we demonstrate that identifying which facts are prone to rapid change can help models avoid reciting outdated information and determine which predictions require seeking out up-to-date knowledge sources. We also show how modeling fact duration improves calibration for knowledge-intensive tasks, such as open-retrieval question answering, under temporal misalignment, by discarding volatile facts. Our data and code are released publicly at https://github.com/mikejqzhang/mitigating_misalignment.
Open AccessMitigating Temporal Misalignment by Discarding Outdated Facts
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. Furthermore, these models are often used under temporal misalignment, tasked with answering questions about the present, despite having only been trained on data collected in the past. To mitigate the effects of temporal misalignment, we propose fact duration prediction: the task of predicting how long a given fact will remain true. In our experiments, we demonstrate that identifying which facts are prone to rapid change can help models avoid reciting outdated information and determine which predictions require seeking out up-to-date knowledge sources. We also show how modeling fact duration improves calibration for knowledge-intensive tasks, such as open-retrieval question answering, under temporal misalignment, by discarding volatile facts. Our data and code are released publicly at https://github.com/mikejqzhang/mitigating_misalignment.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 10485-10500
Exploring Design Choices for Building Language-Specific LLMs
Atula Tejaswi, Nilesh Gupta, Eunsol Choi. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 10485-10500
Open AccessExploring Design Choices for Building Language-Specific LLMs
Atula Tejaswi, Nilesh Gupta, Eunsol Choi. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2069-2085
Crafting In-context Examples according to LMs’ Parametric Knowledge
Yoonsang Lee, Pranav Atreya, Xi Ye, Eunsol Choi. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2069-2085
Open AccessCrafting In-context Examples according to LMs’ Parametric Knowledge
Yoonsang Lee, Pranav Atreya, Xi Ye, Eunsol Choi. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.
- Open Access
Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs
Resolving ambiguities through interaction is a hallmark of natural language, and modeling this behavior is a core challenge in crafting AI assistants. In this work, we study such behavior in LMs by proposing a task-agnostic framework for resolving ambiguity by asking users clarifying questions. Our framework breaks down this objective into three subtasks: (1) determining when clarification is needed, (2) determining what clarifying question to ask, and (3) responding accurately with the new information gathered through clarification. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. For the first subtask, we present a novel uncertainty estimation approach, intent-sim, that determines the utility of querying for clarification by estimating the entropy over user intents. Our method consistently outperforms existing uncertainty estimation approaches at identifying predictions that will benefit from clarification. When only allowed to ask for clarification on 10% of examples, our system is able to double the performance gains over randomly selecting examples to clarify. Furthermore, we find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs. Together, our work lays foundation for studying clarifying interactions with LMs.
Open AccessClarify When Necessary: Resolving Ambiguity Through Interaction with LMs
Resolving ambiguities through interaction is a hallmark of natural language, and modeling this behavior is a core challenge in crafting AI assistants. In this work, we study such behavior in LMs by proposing a task-agnostic framework for resolving ambiguity by asking users clarifying questions. Our framework breaks down this objective into three subtasks: (1) determining when clarification is needed, (2) determining what clarifying question to ask, and (3) responding accurately with the new information gathered through clarification. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. For the first subtask, we present a novel uncertainty estimation approach, intent-sim, that determines the utility of querying for clarification by estimating the entropy over user intents. Our method consistently outperforms existing uncertainty estimation approaches at identifying predictions that will benefit from clarification. When only allowed to ask for clarification on 10% of examples, our system is able to double the performance gains over randomly selecting examples to clarify. Furthermore, we find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs. Together, our work lays foundation for studying clarifying interactions with LMs.
- Open Access
Continually Improving Extractive QA via Human Feedback
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 questions, receive model-predicted answers, and provide feedback. We conduct experiments involving thousands of user interactions under diverse setups to broaden the understanding of learning from feedback over time. Our experiments show effective improvement from user feedback of extractive QA models over time across different data regimes, including significant potential for domain adaptation.
Open AccessContinually Improving Extractive QA via Human Feedback
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 questions, receive model-predicted answers, and provide feedback. We conduct experiments involving thousands of user interactions under diverse setups to broaden the understanding of learning from feedback over time. Our experiments show effective improvement from user feedback of extractive QA models over time across different data regimes, including significant potential for domain adaptation.
- Open Access
Understanding Retrieval Augmentation for Long-Form Question Answering
We present a study of retrieval-augmented language models (LMs) on long-form question answering. We analyze how retrieval augmentation impacts different LMs, by comparing answers generated from models while using the same evidence documents, and how differing quality of retrieval document set impacts the answers generated from the same LM. We study various attributes of generated answers (e.g., fluency, length, variance) with an emphasis on the attribution of generated long-form answers to in-context evidence documents. We collect human annotations of answer attribution and evaluate methods for automatically judging attribution. Our study provides new insights on how retrieval augmentation impacts long, knowledge-rich text generation of LMs. We further identify attribution patterns for long text generation and analyze the main culprits of attribution errors. Together, our analysis reveals how retrieval augmentation impacts long knowledge-rich text generation and provide directions for future work.
Open AccessUnderstanding Retrieval Augmentation for Long-Form Question Answering
We present a study of retrieval-augmented language models (LMs) on long-form question answering. We analyze how retrieval augmentation impacts different LMs, by comparing answers generated from models while using the same evidence documents, and how differing quality of retrieval document set impacts the answers generated from the same LM. We study various attributes of generated answers (e.g., fluency, length, variance) with an emphasis on the attribution of generated long-form answers to in-context evidence documents. We collect human annotations of answer attribution and evaluate methods for automatically judging attribution. Our study provides new insights on how retrieval augmentation impacts long, knowledge-rich text generation of LMs. We further identify attribution patterns for long text generation and analyze the main culprits of attribution errors. Together, our analysis reveals how retrieval augmentation impacts long knowledge-rich text generation and provide directions for future work.
- Open Access
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation
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 spanning hundreds of words, make inference substantially more expensive. We propose compressing the retrieved documents into textual summaries prior to in-context integration. This not only reduces the computational costs but also relieves the burden of LMs to identify relevant information in long retrieved documents. We present two compressors -- an extractive compressor which selects useful sentences from retrieved documents and an abstractive compressor which generates summaries by synthesizing information from multiple documents. Both compressors are trained to improve LMs' performance on end tasks when the generated summaries are prepended to the LMs' input, while keeping the summary concise.If the retrieved documents are irrelevant to the input or offer no additional information to LM, our compressor can return an empty string, implementing selective augmentation.We evaluate our approach on language modeling task and open domain question answering task. We achieve a compression rate of as low as 6% with minimal loss in performance for both tasks, significantly outperforming the off-the-shelf summarization models. We show that our compressors trained for one LM can transfer to other LMs on the language modeling task and provide summaries largely faithful to the retrieved documents.
Open AccessRECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation
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 spanning hundreds of words, make inference substantially more expensive. We propose compressing the retrieved documents into textual summaries prior to in-context integration. This not only reduces the computational costs but also relieves the burden of LMs to identify relevant information in long retrieved documents. We present two compressors -- an extractive compressor which selects useful sentences from retrieved documents and an abstractive compressor which generates summaries by synthesizing information from multiple documents. Both compressors are trained to improve LMs' performance on end tasks when the generated summaries are prepended to the LMs' input, while keeping the summary concise.If the retrieved documents are irrelevant to the input or offer no additional information to LM, our compressor can return an empty string, implementing selective augmentation.We evaluate our approach on language modeling task and open domain question answering task. We achieve a compression rate of as low as 6% with minimal loss in performance for both tasks, significantly outperforming the off-the-shelf summarization models. We show that our compressors trained for one LM can transfer to other LMs on the language modeling task and provide summaries largely faithful to the retrieved documents.
- Open Access
When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants
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 points) at which efficient Transformer variants become more efficient than vanilla models, using a variety of efficiency metrics (latency, throughput, and memory). To conduct this analysis for speech, we introduce L-HuBERT, a novel local-attention variant of a self-supervised speech model. We observe that these thresholds are (a) much higher than typical dataset sequence lengths and (b) dependent on the metric and modality, showing that choosing the right model depends on modality, task type (long-form vs. typical context) and resource constraints (time vs. memory). By visualising the breakdown of the computational costs for transformer components, we also show that non-self-attention components exhibit significant computational costs. We release our profiling toolkit at https://github.com/ajd12342/profiling-transformers .
Open AccessWhen to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants
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 points) at which efficient Transformer variants become more efficient than vanilla models, using a variety of efficiency metrics (latency, throughput, and memory). To conduct this analysis for speech, we introduce L-HuBERT, a novel local-attention variant of a self-supervised speech model. We observe that these thresholds are (a) much higher than typical dataset sequence lengths and (b) dependent on the metric and modality, showing that choosing the right model depends on modality, task type (long-form vs. typical context) and resource constraints (time vs. memory). By visualising the breakdown of the computational costs for transformer components, we also show that non-self-attention components exhibit significant computational costs. We release our profiling toolkit at https://github.com/ajd12342/profiling-transformers .