Research
My current research focuses on enhancing large language models (LLMs) for social good, with an emphasis on health-related domains. I am actively working on post-training (reinforcement learning and preference learning) and synthetic data generation to equip LLMs with complex and reliable abilities. Besides, I am interested in language agents and vision LLMs.
I am looking for a Research Intern position next summer. Feel free to reach out!
|
Preference Learning Unlocks LLMs’ Psycho-Counseling Skills
Mian Zhang,
Shaun M. Eack,
Zhiyu Zoey Chen
Preprint
arXiv
/
code
/
dataset and models
We create a high-quality preference dataset, Psycho-Preference with 36k preference comparison pairs, that align with the preference of professional therapists and use preference learning to train helpful assistants for psycho-counseling.
|
CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Mian Zhang*,
Xianjun Yang*,
Xinlu Zhang,
Travis Labrum,
Jamie C. Chiu,
Shaun M. Eack,
Fei Fang,
William Yang Wang,
Zhiyu Zoey Chen
NAACL 2025 (Accepted)
arXiv
/
dataset
We present the first systematic benchmark to evaluate LLMs' efficacy for CBT. The key finding is while LLMs excel at recalling CBT knowledge, they struggle with complex tasks requiring deep cognitive analysis and patient-specific responses.
|
IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
Kaiyu He,
Mian Zhang,
Shuo Yan,
Peilin Wu,
Zhiyu Zoey Chen
Preprint
arXiv
/
code and data
We propose IDEA, a holistic LLM agent framework integrating Induction, DEduction, and Abduction, to generate hypotheses, devise plans, and revise hypotheses iteratively to learn new rules in novel environments and RULEARN, a novel benchmark to assess the
rule-learning abilities of LLM agents in interactive settings.
|
Large Language Models for Disease Diagnosis: A Scoping Review
Shuang Zhou*,
Zidu Xu*,
Mian Zhang*,
Chunpu Xu*,
Yawen Guo,
Zaifu Zhan,
Sirui Ding,
Jiashuo Wang,
Kaishuai Xu,
Yi Fang,
Liqiao Xia,
Jeremy Yeung,
Daochen Zha,
Mingquan Lin,
Rui Zhang
Preprint
arXiv
We perform a comprehensive review of LLM-based methods for disease diagnosis.
|
Inconsistent dialogue responses and how to recover from them
Mian Zhang,
Lifeng Jin,
Linfeng Song,
Haitao Mi,
Dong Yu
EACL 2024
paper
/
code and dataset
We propose a comprehensive dataset for studying the inconsistencies in dialogue, which covers the life span of inconsistencies, namely introduction, understanding, and resolution.
|
SafeConv: Explaining and Correcting Conversational Unsafe Bahavior
Mian Zhang,
Lifeng Jin,
Linfeng Song,
Haitao Mi,
Wenliang Chen,
Dong Yu
ACL 2023   (Oral Presentation)
paper
/
dataset
We construct a high-quality dataset called SafeConv for conversational safety and train a powerful utterance rewriter to correct unsafe content with Reinforcement Learning from Human Feedback (PPO).
|
Friend-training: Learning from Different but Related Tasks
Mian Zhang,
Lifeng Jin,
Linfeng Song,
Haitao Mi,
Dong Yu
EACL 2023
paper
We propose friend-training, a cross-task self-training framework, where models trained to do different tasks are used in an iterative training, pseudo-labeling, and retraining process to help each other for better selection of pseudo-labels.
|
A Pairing Enhancement Approach for Aspect Sentiment Triplet Extraction
Fang Yang,
Mian Zhang,
Gongzhen Hu,
Xiabing Zhou
KSEM 2023
paper
We propose a pairing enhancement approach for ASTE, which incorporates contrastive learning during the training stage to inject aspect-opinion pairing knowledge into the triplet extraction model.
|
Emotion Recognition in Conversation from Variable-Length Context
Mian Zhang,
Xiabing Zhou
Wenliang Chen,
Min Zhang
ICASSP 2023
paper
We propose a mixture of experts network that leverages variable-length context windows when predicting the emotion of different utterances.
|
Teaching
|
Human Language Technologies (CS4395) at UTD (Teaching Assistant) - Fall, 2024
Data Structures and Algorithms (CS3114) at VT (Teaching Assistant) - Spring, 2024
Intermediate Programming in Python (CS2064) at VT (Teaching Assistant) - Fall, 2023
|
|