I am a last-year PhD student in PolyU NLP Group at The Hong Kong Polytechnic University, fortunately advised by Prof. Maggie Wenjie Li.

I am interested in 💡 LLM-based reasoning, 🤖 Conversational AI and 🩺 Medical AI. Recently, I focus on the following topics:

  • Interpretable Medical Dialogue Systems involving diagnosis, prescriptions, concultations, etc. I am committed to enabling machines to function as reliable and trustworthy clinicians;
  • Mathematical Reasoning;
  • Other applications empowered by Large Language Models (LLMs). My focus lies on reasoning.

🔥🔥🔥 I am available on the job market and actively looking for industry opportunities!

Recent News

[Sept 2024] Two papers has been accepted by EMNLP 2024.
[May 2024] I am honored to receive an invitation from Stanford MedAI, and I will be giving a talk about medical dialogue on May 20th. [Video].
[May 2024] One paper has been accepted by ACL 2024 Findings.
[Dec 2023] I will attend the EMNLP 2023 conference in Singapore.
[Oct 2023] Our paper RECAP has been accepted by EMNLP 2023 Findings.
[May 2023] Our paper ORGAN and DFMed have been accepted by ACL 2023 Main proceedings and Findings.

Publications

* indicates equal contribution. Full list can be found in my Google Scholar.

♾️ Subtle Errors Matter: Preference Learning via Error-injected Self-editing
Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li
[paper]

Integrative Decoding: Improve Factuality via Implicit Self-consistency
Yi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao, Song Wang, Yuji Zhang, Wenjun Hou, Kaishuai Xu, Wenge Liu, Wenjie Li, Jian Jiao, Qi Chen, Peng Cheng, Wayne Xiong
[paper]

😇 AutoPal: Autonomous Adaptation to Users for Personal AI Companisonship
Yi Cheng, Wenge Liu, Kaishuai Xu, Wenjun Hou, Yi Ouyang, Chak Tou Leong, Xian Wu, Yefeng Zheng
arXiv: 2406.13960, 2024
[paper]

👿 No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks
Chak Tou Leong, Yi Cheng, Kaishuai Xu, Jian Wang, Hanlin Wang, Wenjie Li
arXiv: 2405.16229, 2024
[paper]

🎧 When LLMs meets acoustic landmarks: An efficient approach to integrate speech into large language models for depression detection Xiangyu Zhang, Hexin Liu, Kaishuai Xu, Qiquan Zhang, Daijiao Liu, Beena Ahmed, Julien Epps
EMNLP 2024
[paper]

🩺 Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignment
Kaishuai Xu, Yi Cheng*, Wenjun Hou*, Qiaoyu Tan, Wenjie Li
ACL 2024 Findings
[paper] [code]  

🩻 ICON: Improving Inter-Report Consistency of Radiology Report Generation via Lesion-aware Mix-up Augmentation
Wenjun Hou, Yi Cheng*, Kaishuai Xu*, Yan Hu, Wenjie Li, Jiang Liu
EMNLP 2024 Findings
[paper] [code]  

🩺 Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis
Kaishuai Xu, Wenjun Hou, Yi Cheng, Jian Wang, Wenjie Li
arXiv: 2401.06541, 2024
[paper]

🩻 RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning
Wenjun Hou, Yi Cheng*, Kaishuai Xu*, Wenjie Li, Jiang Liu
EMNLP 2023 Findings
[paper] [code]  

🩺 Medical Dialogue Generation via Dual Flow Modeling
Kaishuai Xu, Wenjun Hou*, Yi Cheng*, Jian Wang, Wenjie Li
ACL 2023 Findings
[paper] [code]  

🩻 ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning
Wenjun Hou, Kaishuai Xu*, Yi Cheng*, Wenjie Li, Jiang Liu
ACL 2023
[paper] [code]  

Activities

Review: EMNLP 2022
Talk: Behave like a Doctor: Clinical Process-Aware Medical Dialogue System. Stanford MedAI Group Exchange Sessions. May 20, 2024.