Mian Zhang

Hi, I'm a CS PhD in UTD, advised by Zhiyu Zoey Chen. I was a research intern at Tencent AI Lab and a member of the NLP group at Soochow University.

Email  /  CV  /  Scholar  /  Twitter  /  Github

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 techniques 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!

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.

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.

We perform a comprehensive review of LLM-based methods for disease diagnosis. Our review examines the existing literature across various dimensions, including disease types and associated clinical specialties, clinical data, LLM techniques, and evaluation methods. Additionally, we offer recommendations for applying and evaluating LLMs for diagnostic tasks. Furthermore, we assess the limitations of current research and discuss future directions.

We propose the first comprehensive dataset for studying the inconsistencies in dialogue, which covers the life span of inconsistencies, namely introduction, understanding, and resolution. Our experimental findings indicate that our dataset significantly helps the progress in identifying and resolving conversational inconsistencies, and current popular large language models like ChatGPT which are good at resolving inconsistencies however still struggle with detection.

We construct a new dataset called SafeConv for the research of conversational safety. SafeConv could power multiple models to detect, explain, and correct conversational unsafe behavior.

We propose Friend-traing, 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.

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.

We propose a new method to leverage variable-length context windows when predicting the emotion of different utterances.