Lucy Lu Wang
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
Research Subjects
Lucy Lu Wang has a total of 321 co-authors. Here are the top co-authors by number of shared publications:
- Kyle Lo
Allen Institute for AI
12 shared publications Kyle Lo
Allen Institute for AI
8 shared publications- Doug Downey
Allen Institute for Artificial Intelligence
5 shared publications Rodney Kinney
Allen Institute for AI
5 shared publicationsChris Wilhelm
Allen Institute for AI
4 shared publicationsDaniel S. Weld
Allen Institute for AI
4 shared publications
Latest Publications
- Open Access
- 24 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists
- 24 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Open AccessQuerying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 7864-7892
Beyond Readability Metrics: Plain Language Priorities in Disability Advocacy Organizations
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 7864-7892
Open AccessBeyond Readability Metrics: Plain Language Priorities in Disability Advocacy Organizations
- Open Access
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 588-604
ReFinE: Streamlining UI Mockup Iteration with Research Findings
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 588-604
Open AccessReFinE: Streamlining UI Mockup Iteration with Research Findings
- Open Access
- 15 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 33 (2) , 1-31
Passing the Buck to AI: How Individuals’ Decision-Making Patterns Affect Reliance on AI
Psychological research has identified different patterns individuals have while making decisions, such as vigilance (making decisions after thorough information gathering), hypervigilance (rushed and anxious decision-making), and buckpassing (deferring decisions to others). We examine whether these decision-making patterns affect peoples’ engagement with AI-generated information in decision-making. In an online experiment with 810 participants tasked with distinguishing food facts from myths, we found that a higher buckpassing tendency was positively correlated with the likelihood of seeking AI information and reported reliance on AI, while being negatively correlated with the time spent reading AI explanations. In contrast, the higher a participant tended towards vigilance, the more carefully they scrutinized the AI’s information, as indicated by an increased time spent looking through the AI’s explanations. These findings suggest that a person’s decision-making pattern plays a significant role in their interactions with AI suggestions, which provides a new understanding of individual differences in AI-assisted decision-making.
- 15 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 33 (2) , 1-31
Open AccessPassing the Buck to AI: How Individuals’ Decision-Making Patterns Affect Reliance on AI
Psychological research has identified different patterns individuals have while making decisions, such as vigilance (making decisions after thorough information gathering), hypervigilance (rushed and anxious decision-making), and buckpassing (deferring decisions to others). We examine whether these decision-making patterns affect peoples’ engagement with AI-generated information in decision-making. In an online experiment with 810 participants tasked with distinguishing food facts from myths, we found that a higher buckpassing tendency was positively correlated with the likelihood of seeking AI information and reported reliance on AI, while being negatively correlated with the time spent reading AI explanations. In contrast, the higher a participant tended towards vigilance, the more carefully they scrutinized the AI’s information, as indicated by an increased time spent looking through the AI’s explanations. These findings suggest that a person’s decision-making pattern plays a significant role in their interactions with AI suggestions, which provides a new understanding of individual differences in AI-assisted decision-making.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Science and Technology for Augmenting Reading (STAR)
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessScience and Technology for Augmenting Reading (STAR)
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1917-1937
SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1917-1937
Open AccessSusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents
- Open Access
Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
Real-world visual question answering (VQA) is often context-dependent: an image-question pair may be under-specified, such that the correct answer depends on external information that is not observable in the image. In such cases, directly answering can lead to confident but incorrect predictions. We propose CoA(Clarify-or-Answer), an ask-or-answer agent that separately models the decision to ask or answer, and what to ask if needed. CoA first determines whether clarification is necessary; if so, it asks a single focused question and then incorporates the response to produce the final answer. We introduce CONTEXTCLARIFY with a set of ambiguous VQA questions and the contrast set that is non-ambiguous. We further introduce GRPO-CR (Clarification Reasoning), a reinforcement learning approach that optimizes clarification question generation with multiple reward signals encouraging well-formed, focused, non-trivial questions that resolve ambiguity. Across three VLLMs and three datasets, CoA achieves consistent improvements at both the module and system levels, improving end-to-end VQA accuracy by an average of +15.3 points (83%) over prompting-based baselines
Open AccessClarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
Real-world visual question answering (VQA) is often context-dependent: an image-question pair may be under-specified, such that the correct answer depends on external information that is not observable in the image. In such cases, directly answering can lead to confident but incorrect predictions. We propose CoA(Clarify-or-Answer), an ask-or-answer agent that separately models the decision to ask or answer, and what to ask if needed. CoA first determines whether clarification is necessary; if so, it asks a single focused question and then incorporates the response to produce the final answer. We introduce CONTEXTCLARIFY with a set of ambiguous VQA questions and the contrast set that is non-ambiguous. We further introduce GRPO-CR (Clarification Reasoning), a reinforcement learning approach that optimizes clarification question generation with multiple reward signals encouraging well-formed, focused, non-trivial questions that resolve ambiguity. Across three VLLMs and three datasets, CoA achieves consistent improvements at both the module and system levels, improving end-to-end VQA accuracy by an average of +15.3 points (83%) over prompting-based baselines
- Open Access
ROBoto2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment
We present ROBOTO2, an open-source, web-based platform for large language model (LLM)-assisted risk of bias (ROB) assessment of clinical trials. ROBOTO2 streamlines the traditionally labor-intensive ROB v2 (ROB2) annotation process via an interactive interface that combines PDF parsing, retrieval-augmented LLM prompting, and human-in-the-loop review. Users can upload clinical trial reports, receive preliminary answers and supporting evidence for ROB2 signaling questions, and provide real-time feedback or corrections to system suggestions. ROBOTO2 is publicly available at https://roboto2.vercel.app/, with code and data released to foster reproducibility and adoption. We construct and release a dataset of 521 pediatric clinical trial reports (8954 signaling questions with 1202 evidence passages), annotated using both manually and LLM-assisted methods, serving as a benchmark and enabling future research. Using this dataset, we benchmark ROB2 performance for 4 LLMs and provide an analysis into current model capabilities and ongoing challenges in automating this critical aspect of systematic review.
Open AccessROBoto2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment
We present ROBOTO2, an open-source, web-based platform for large language model (LLM)-assisted risk of bias (ROB) assessment of clinical trials. ROBOTO2 streamlines the traditionally labor-intensive ROB v2 (ROB2) annotation process via an interactive interface that combines PDF parsing, retrieval-augmented LLM prompting, and human-in-the-loop review. Users can upload clinical trial reports, receive preliminary answers and supporting evidence for ROB2 signaling questions, and provide real-time feedback or corrections to system suggestions. ROBOTO2 is publicly available at https://roboto2.vercel.app/, with code and data released to foster reproducibility and adoption. We construct and release a dataset of 521 pediatric clinical trial reports (8954 signaling questions with 1202 evidence passages), annotated using both manually and LLM-assisted methods, serving as a benchmark and enabling future research. Using this dataset, we benchmark ROB2 performance for 4 LLMs and provide an analysis into current model capabilities and ongoing challenges in automating this critical aspect of systematic review.
- Open Access
- 22 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Benchmarking PDF Accessibility Evaluation: A Dataset and Framework for Assessing Automated and LLM-Based Approaches for Accessibility Testing
- 22 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Open AccessBenchmarking PDF Accessibility Evaluation: A Dataset and Framework for Assessing Automated and LLM-Based Approaches for Accessibility Testing
- Open Access
- 4 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1210-1227
What About My Design Context?: Exploring the Use of Generative AI to Support Customization of Translational Research Artifacts
- 4 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1210-1227
Open AccessWhat About My Design Context?: Exploring the Use of Generative AI to Support Customization of Translational Research Artifacts