Publications

Conference papers · Journal articles · Preprints · Manuscripts

* Equal contribution. + Co-corresponding authors.

Conference papers

2026

MedQA-MM: Shortcuts Behind Medical Visual Reasoning
B. Wang, Y. Zhang, J. Yu, C. Ong, J. Huang, Z. Li, Z. Zhang, A. Cohan, H. Yu, and Z. Yao.
EMNLP 2026 · Preprint

MediSketch: Test-Time Scaling for Multimodal Patient Education
Z. Tang, B. Wang, Z. Zhang, W. Liu, P. Xiang, J. Huang, C. Ong, H. Yu, and Z. Yao.
Findings of EMNLP 2026

LLM-Based Multi-Agent Systems for Clinical Workflows: A Survey of AI Hospitals
Zonghai Yao and Hong Yu.
ACL 2026 · Paper

Exploiting Tree Structure for Credit Assignment in Reinforcement Learning with Large Language Models
Hieu Tran*, Zonghai Yao*, and Hong Yu.
Findings of ACL 2026 · Paper

Medical thinking with multiple images
Z. Yao*, B. Wang*, Y. Zhang, J. Wang, I. Xia, Z. Tang, S. Han, F. Ouyang, Z. Yang, A. Cohan, and H. Yu.
ICLR 2026 · Paper

MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills
Z. Yao, Z. Zhang, C. Tang, X. Bian, Y. Zhao, Z. Yang, J. Wang, H. Zhou, W. Jang, F. Ouyang, and H. Yu.
EACL 2026 (oral) · Paper

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
S. Machcha, S. Yerra, S. Gupta, A. Sahoo, S. Sultana, H. Yu, and Z. Yao.
EACL 2026 (oral) · Paper

ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care
Z. Yao*, T. Chafekar*, J. Wang, S. Han, F. Ouyang, J. Qian, L. Li, and H. Yu.
AAAI 2026, AI for Social Impact · Paper

PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
H. Tran, Z. Yao, N. L. Tran, Z. Yang, F. Ouyang, S. Han, R. Rahimi, and H. Yu.
AAAI 2026 · Paper

2025

DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge
Zonghai Yao*, Michael Sun*, Won Seok Jang, Sunjae Kwon, Soie Kwon, and Hong Yu.
EMNLP 2025 · Paper

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations
B. Wang*, I. Xia*, Y. Zhang, J. Wang, F. Ouyang, S. Han, A. Cohan, H. Yu+, and Z. Yao+.
EMNLP 2025 (oral) · Paper

Chatbot To Help Patients Understand Their Health
W. S. Jang*, H. Tran*, M. Mistry, S. Gandluri, Y. Zhang, S. Sultana, S. Kwon, Z. Yao+, and H. Yu+.
Findings of EMNLP 2025 · Paper

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
H. Tran, Z. Yao, Z. Yang, J. Wang, Y. Zhang, S. Han, F. Ouyang, and H. Yu.
ACL 2025 · Paper

MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback
Z. Yao*, A. Parashar*, H. Zhou, W. S. Jang, F. Ouyang, Z. Yang, and H. Yu.
NAACL 2025 (oral) · Paper

2024

SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
P. Mishra*, Z. Yao*, P. Vashisht, F. Ouyang, B. Wang, V. D. Mody, and H. Yu.
EMNLP 2024 · Paper

README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP
Z. Yao, N. Kantu, G. Wei, H. Tran, Z. Duan, S. Kwon, Z. Yang, and H. Yu.
Findings of EMNLP 2024 · Paper

Large Language Models are In-context Teachers for Knowledge Reasoning
Jiachen Zhao, Zonghai Yao, Zhichao Yang, and Hong Yu.
Findings of EMNLP 2024 · Paper

NoteChat: A Dataset of Synthetic Patient-Physician Conversations Conditioned on Clinical Notes
J. Wang*, Z. Yao*, Z. Yang, H. Zhou, R. Li, X. Wang, Y. Xu, and H. Yu.
Findings of ACL 2024 · Paper

2023

Improving Summarization with Human Edits
Zonghai Yao, Benjamin J. Schloss, and Sai P. Selvaraj.
EMNLP 2023 · Paper

Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
H. Chang*, Z. Yao*, A. Gon, H. Yu, and A. McCallum.
Findings of ACL 2023 · Paper

Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt
Zhichao Yang, Sunjae Kwon, Zonghai Yao, and Hong Yu.
AAAI 2023 · Paper

Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing
Z. Yao, Y. Cao, Z. Yang, and H. Yu.
AMIA 2023 (oral) · Paper

2022

MedJEx: A Medical Jargon Extraction Model with Wiki’s Hyperlink Span and Contextualized Masked Language Model Score
S. Kwon, Z. Yao, H. Jordan, D. Levy, B. Corner, and H. Yu.
EMNLP 2022 · Paper

Extracting Biomedical Factual Knowledge Using Pretrained Language Model and Electronic Health Record Context
Z. Yao, Y. Cao, Z. Yang, V. Deshpande, and H. Yu.
AMIA 2022 (oral) · Paper

2021

Improving Formality Style Transfer with Context-Aware Rule Injection
Zonghai Yao and Yu Hong.
ACL 2021 · Paper

2020

Zero-shot Entity Linking with Efficient Long Range Sequence Modeling
Zonghai Yao, Liangliang Cao, and Huapu Pan.
Findings of EMNLP 2020 · Paper

Journal articles

2026

Toward Reviewable Medical Evidence Synthesis for Care Delivery
Zonghai Yao and Hong Yu.
npj Digital Medicine, 2026 (Perspective) · Paper

Patient Journey Evaluation for Consumer AI Health Assistants
Zonghai Yao and Hong Yu.
npj Digital Medicine, 2026 (Perspective) · Paper

SynthEHR-eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data
Z. Yao*, Y. Zhao*, A. Mitra, D. Levy, E. Druhl, J. Tsai, and H. Yu.
npj Digital Medicine, 2026 · Paper

MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis
J. Wang, Z. Yao, Y. Ting, E. Chen, H. Tran, H. Yu, W. Huang, and T. Chen.
Transactions of the Association for Computational Linguistics (TACL), 2026 · Preprint

Posttraumatic Stress Disorder, Health-Related Social Needs, and Cognitive Outcomes in US Veterans
F. Ouyang, T. Pogoda, J. Reisman, R. Li, R. Pradhan, Y. Moradi, J. Mez, W. Liu, Y. Zhang, S. Sultana, J. Qian, Z. Yao, A. Mitra, and H. Yu.
JAMA Network Open, 2026 · Paper

Socioeconomic, Demographic and Geographic Disparities in Accessibility to Food Pantries in the United States
Y. Zhang, M. Lee, J. Gibbons, H. Chen, Y. Wang, Z. Yao, O. Bennett, F. Ouyang, D. Levy, K. Tucker, and H. Yu.
Scientific Reports, 2026 · Paper

Enhancing Large Language Models for Identifying and Prioritizing Important Medical Jargons From Electronic Health Record Notes Using Data Augmentation: Comparative Study
W. Jang*, S. Sultana*, Z. Yao*, H. Tran, Z. Yang, S. Kwon, and H. Yu.
JMIR AI, 2026 · Paper

2025

Unveiling GPT-4V’s Hidden Challenges Behind High Accuracy on USMLE Questions: Observational Study
Z. Yang*, Z. Yao*, M. Tasmin, P. Vashisht, W. Jang, F. Ouyang, B. Wang, D. McManus, D. Berlowitz, and H. Yu.
Journal of Medical Internet Research (JMIR), 2025 · Paper

Association between PTSD and health-related social needs in US Veterans
F. Ouyang, W. Hu, J. Reisman, T. Pogoda, K. Carlson, W. Liu, Y. Moradi, Y. Zhang, S. Han, S. Sultana, W. Jang, Z. Yao, A. Mitra, and H. Yu.
Journal of Affective Disorders, 2025 · Paper

Development of a Surveillance System to Identify Incidence of Evictions Among Patients in Veterans Affairs Medical Centers Across the United States
J. Tsai, S. S. Rajan, Z. Yao, J. Reisman, W. Liu, and H. Yu.
Journal of Community Health, 2025 · Paper

2024

BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing
Hieu Tran, Zhichao Yang, Zonghai Yao, and Hong Yu.
Journal of the American Medical Informatics Association (JAMIA), 2024 · Paper

2023

PaniniQA: Enhancing Patient Education Through Interactive Question Answering
P. Cai*, Z. Yao*, F. Liu, D. Wang, M. Reilly, H. Zhou, L. Li, Y. Cao, A. Kapoor, A. Bajracharya, D. Berlowitz, and H. Yu.
TACL, 2023 · Paper

Automated Identification of Eviction Status from Electronic Health Record Notes
Z. Yao, J. Tsai, W. Liu, D. Levy, E. Druhl, J. Reisman, and H. Yu.
JAMIA, 2023 · Paper

2021

Named Entity Location Prediction Combining Twitter and Web
Y. Liu, W. Shen, Z. Yao, J. Wang, Z. Yang, and X. Yuan.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021 · Paper

Preprints

2026

TARSE: Test-Time Adaptation via Retrieval of Skills and Experience for Reasoning Agents
J. Wang, Z. Yao, H. Zeng, Z. Yang, H. Zamani, and H. Yu.
Preprint, 2026 · Paper

Rethinking Patient Education as Multi-turn Multi-modal Interaction
Zonghai Yao*, Zhipeng Tang*, Chengtao Lin, Xiong Luo, Benlu Wang, Juncheng Huang, Chin Siang Ong, and Hong Yu.
Preprint, 2026 · Paper

2025

ChatThero: A Language Agent for Recovery Support
J. Wang*, Z. Yao*, Z. Yang, J. Qian, L. Li, and H. Yu.
Preprint, 2025 · Earlier preprint

MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning
Hieu Tran*, Zonghai Yao*, Won Seok Jang, Sharmin Sultana, Allen Chang, Yuan Zhang, and Hong Yu.
Preprint, 2025 · Paper

2024

JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability
Junda Wang, Zhichao Yang, Zonghai Yao, and Hong Yu.
Preprint, 2024 · Paper

Manuscripts

Multi-Agent Deep Research for Healthcare Predictions
J. Wang, M. Ghaffari, T. Chafekar, Z. Zhang, Y. Zhang, H. Yu, C. Morato, and Z. Yao.
Manuscript

When Evidence Changes: Temporal Grounding across Agent Autonomy Levels
J. Wang, Z. Yao, H. Zeng, M. Ghaffari, Z. Zhang, C. Morato, H. Zamani, and H. Yu.
Manuscript

Evaluating Evidence Use in Medical Deep Research for Diagnostic Decision Support
X. Lu, B. Wang, J. Wang, C. Ong, J. Huang, Y. Zhang, Z. Tang, Z. Zhang, H. Yu, and Z. Yao.
Manuscript

Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement Learning
H. Tran, Z. Yao, S. Kwon, and H. Yu.
Manuscript

ResidualForge: Toward Autonomous Improvement of Tool-Using Agent Teams
J. Wang, Z. Yao, M. Ghaffari, H. Yu, and C. Morato.
Manuscript

Learning to Consult Specialist for Medical Visual Reasoning
H. Tran, Z. Yao, J. Wang, B. Wang, J. Huang, C. Ong, and H. Yu.
Manuscript