11 citations · 38 across the 31 of their papers we have counts for
37 papers
ArcFlow: Training Flow Policies for Multiple Solver Budgets
Hieu Tran, Hong Yu
Flow-matching policies adjust inference cost through the number of solver steps, but reinforcement learning at a single fixed solver budget can hide degradation at cheaper deployme…
Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets
Hieu Tran, Hong Yu
Evaluations of large language model (LLM) agents report that pricing agents collude at others' expense. Yet collusion is defined by enforcement: a cartel, in which competitors shar…
Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement Learning
Hieu Tran, Zonghai Yao, Sunjae Kwon +1
Training tool-using language models requires costly interaction, yet identical rewards within a rollout group provide no group-relative learning signal. We use reward disagreement…
Second Thoughts: Exploring and Planning through Comparative Imagination in World Models
Hieu Tran, Hong Yu
World models let agents compare imagined outcomes before acting, but an agent must still decide which alternatives to explore and when a proposed plan should replace its learned po…
DischargeBench: Pre-Deployment Evaluation of LLM Discharge Educators through Persona-Grounded Patient Simulation
Won Seok Jang, Zonghai Yao, Youngbin Jang +3
Effective discharge education is personalized: a clinician adapts the discharge plan to each patient's literacy, recall, and personality. Before large language models (LLMs) take o…
MUSES: A Benchmark for Prospective Intellectual-Roots Retrieval
Rohan Pandey, Sunjae Kwon, Hong Yu
Scientific discovery depends on finding prior literature that shapes what comes next. Existing retrieval systems optimize for relevance and popularity, often favoring central paper…
Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecasting
Junda Wang, Meysam Ghaffari, Akshat Choube +3
Next-encounter ICD forecasting predicts which standardized diagnosis codes will be documented at a future visit from the longitudinal record available beforehand. The task is prosp…
Chatbot To Help Patients Understand Their Health
Won Seok Jang, Hieu Tran, Manav Mistry +7
Patients must possess the knowledge necessary to actively participate in their care. We present NoteAid-Chatbot, a conversational AI that promotes patient understanding via a novel…
Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
Hieu Tran, Zonghai Yao, Hong Yu
Reinforcement learning improves LLM reasoning, yet sparse delayed reward over long sequences makes token-level credit assignment the key bottleneck. We study the verifiable-reward…
DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge
Zonghai Yao, Michael Sun, Won Seok Jang +3
Discharge communication is a critical yet underexplored component of patient care, where the goal shifts from diagnosis to education. While recent large language model (LLM) benchm…
MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework
Md Shahidul Salim, Lian Fu, Arav Adikesh Ramakrishnan +2
We present MedCOD (Medical Chain-of-Dictionary), a hybrid framework designed to improve English-to-Spanish medical translation by integrating domain-specific structured knowledge i…
PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
Hieu Tran, Zonghai Yao, Nguyen Luong Tran +5
Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Rea…
From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations
Benlu Wang, Iris Xia, Yifan Zhang +6
Large language models (LLMs) have demonstrated promising performance on medical benchmarks; however, their ability to perform medical calculations, a crucial aspect of clinical dec…
ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care
Zonghai Yao, Talha Chafekar, Junda Wang +5
Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse behavioral, psychosocial, and so…
ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery
Junda Wang, Zonghai Yao, Lingxi Li +3
Substance use disorders (SUDs) affect millions of people, and relapses are common, requiring multi-session treatments. Access to care is limited, which contributes to the challenge…
MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning
Hieu Tran, Zonghai Yao, Won Seok Jang +4
Generative AI has demonstrated strong potential in healthcare, from clinical decision support to patient-facing chatbots that improve outcomes. A critical challenge for deployment…
Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study
Won Seok Jang, Sharmin Sultana, Zonghai Yao +4
OpenNotes gives patients access to their EHR notes, but dense medical jargon limits comprehension. We evaluate closed-source and open-source LLMs for extracting and prioritizing th…
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
Hieu Tran, Zonghai Yao, Junda Wang +3
This work introduces RARE (Retrieval-Augmented Reasoning Enhancement), a versatile extension to the mutual reasoning framework (rStar), aimed at enhancing reasoning accuracy and fa…
MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis
Junda Wang, Yujan Ting, Zonghai Yao +5
Medical multimodal large language models (MLLMs) can perform well on existing medical visual question answering (MedVQA) benchmarks, but their training data often does not match cl…
Blocks Architecture (BloArk): Efficient, Cost-Effective, and Incremental Dataset Architecture for Wikipedia Revision History
Lingxi Li, Zonghai Yao, Sunjae Kwon +1
Wikipedia (Wiki) is one of the most widely used and publicly available resources for natural language processing (NLP) applications. Wikipedia Revision History (WikiRevHist) shows…
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine
Jiatan Huang, Mingchen Li, Zonghai Yao +8
Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs), as the relational path informat…
MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback
Zonghai Yao, Aditya Parashar, Huixue Zhou +4
Automatic question generation (QG) is essential for AI and NLP, particularly in intelligent tutoring, dialogue systems, and fact verification. Generating multiple-choice questions…
MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills
Zonghai Yao, Zihao Zhang, Chaolong Tang +8
Artificial intelligence (AI) and large language models (LLMs) in healthcare require advanced clinical skills (CS), yet current benchmarks fail to evaluate these comprehensively. We…
ReadCtrl: Personalizing text generation with readability-controlled instruction learning
Hieu Tran, Zonghai Yao, Lingxi Li +1
Content generation conditioning on users's readability is an important application for personalization. In an era of large language models (LLMs), readability-controlled text gener…