Jiashuo WANG is a Postdoctoral Fellow in the Department of Computing at The Hong Kong Polytechnic University, where she collaborates with Prof. Johan F. Hoorn and Prof. Wenjie Li. Her research centers on interactive large language models, with a particular focus on emotion-aware conversation and socially-driven dialogue systems. She is also deeply committed to socially responsible NLP and the broader application of NLP for social good. She received both her PhD and BSc in Computer Science from The Hong Kong Polytechnic University, where her doctoral research was supervised by Prof. Wenjie Li. Her PhD years were further enriched by a visiting studentship at the University of Chicago hosted by Dr. Chenhao Tan, and a research internship at Microsoft Research Asia, Shanghai, mentored by Kaitao Song.

Publications

Scale: Selective resource allocation for overcoming performance bottlenecks in mathematical test-time scaling Yang Xiao, Chunpu Xu, Ruifeng Yuan, Jiashuo WANG, Wenjie Li, Pengfei Liu AAAI 2026   • Paper

Uncertainty-aware large language models for explainable disease diagnosis Shuang Zhou, Jiashuo WANG, Zidu Xu, Song Wang, David Brauer, Lindsay Welton, Jacob Cogan, Yuen-Hei Chung, Lei Tian, Zaifu Zhan, Yu Hou, Mingquan Lin, Genevieve B. Melton, Rui Zhang npj Artificial Intelligence   • Paper

Explainable differential diagnosis with dual-inference large language models Shuang Zhou, Mingquan Lin, Sirui Ding, Jiashuo WANG, Canyu Chen, Genevieve B Melton, James Zou, Rui Zhang npj Artificial Intelligence   • Paper

Large language models for disease diagnosis: A scoping review Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jiashuo WANG, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang npj Artificial Intelligence   • Paper

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling Yang Xiao, Jiashuo WANG, Ruifeng Yuan, Chunpu Xu, Kaishuai Xu, Wenjie Li, Pengfei Liu NeurIPS 2025   • Paper

MIO: A Foundation Model on Multimodal Tokens Shuang Zhou, Mingquan Lin, Sirui Ding, Jiashuo WANG, Canyu Chen, Genevieve B Melton, James Zou, Rui Zhang EMNLP 2025   • Paper

Evaluating LLM Adaptation to Temporal Evolution of Human States Yang Xiao*, Jiashuo WANG*, Qiancheng Xu, Changhe Song, Chunpu Xu, Yi Cheng, Wenjie Li, Pengfei Liu (*: Equal contribution) ACL 2025   • Paper

Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback Jiashuo WANG, Chunpu Xu, Chak Tou Leong, Wenjie Li, Jing Li ACL 2024 (Findings)   • Paper • Codes

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue Jian Wang, Chak Tou Leong, Jiashuo WANG, Dongding Lin, Wenjie Li, Xiao-Yong Wei ACL 2024   • Paper • Codes

Aligning Language Models with Human Preferences via a Bayesian Approach Jiashuo WANG, Haozhao Wang, Shichao Sun, Wenjie Li NeurIPS 2023   • Paper • Codes • Video (in Chinese)

Self-Detoxifying Language Models via Toxification Reversal Chak Tou Leong, Yi Cheng, Jiashuo WANG, Jian Wang, Wenjie Li EMNLP 2023   • Paper • Codes

CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation Jiashuo WANG, Yi Cheng, Wenjie Li EMNLP 2022 (Findings)   • Paper • Codes

Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality Jiashuo WANG, Wenjie Li, Peiqin Lin, Feiteng Mu Knowledge-Based Systems 2021   • Paper

Professional Activities

Teaching Assistant

COMP2012 Discrete Mathematics 2023 Fall COMP5423 Natural Language Processing 2023 Spring, 2022 Spring, 2021 Spring COMP2411 Database Systems 2022 Fall COMP4431 Artificial Intelligence 2021 Fall

Academic Service

Reviewer: ARR 2023 ~ 2026; KDD 2023; EMNLP 2022

Area Chair: ICLR 2026 LLA Workshop

Demo Projects

Auto Coffee Machine Robot: This project aims to build a coffee machine robot that can provide guests with a cup of coffee in three steps: (i) identifying and greeting a newly arrived guest through a screen; (ii) recommending a type of coffee after chatting with the guest; and (iii) notifying the guest to pick up the coffee when it is ready. My responsibility in this project was to develop the module that enables the robot to engage in chit-chat with users in step (ii).   • Demo Video • Overview Figure

Emotion-Aware Conversation Agent Demonstration

Last update: March 2026