Hi! I am a fourth-year PhD candidate at The Chinese University of Hong Kong, advised by Prof. Kam-Fai Wong. Previously, I obtained my undergraduate degree in computer science from Hong Kong Baptist University, with a minor in statistics.

My research interests lie primarily in natural language processing (NLP) and machine learning. I am mostly interested in dialog agents, particularly in task-oriented dialog systems in my early years of study. Recently, I have been working on understanding the capabilities of large language models.

Publications

(* indicates equal contribution)

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, and Kam-Fai Wong
Preprint 2024. [code]

JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning
Wai-Chung Kwan*, Huimin Wang*, Hongru Wang, Zezhong Wang, Xian Wu, Yefeng Zheng, and Kam-Fai Wong.
COLING 2024 (Long papers). [code]

M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models
Wai-Chung Kwan, Xingshan Zeng, Yufei Wang, Yusen Sun, Liangyou Li, Lifeng Shang, Qun Liu, and Kam-Fai Wong
Preprint 2023. [code]

Dialog Action-Aware Transformer for Dialog Policy Learning
Huimin Wang*, Wai-Chung Kwan*, and Kam-Fai Wong.
SIGDIAL 2023 (short papers). [poster]

CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation
Huimin Wang*, Wai-Chung Kwan*, and Kam-Fai Wong.
ACL 2023 (long papers). [code]

A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning
Wai-Chung Kwan*, Hongru Wang*, Huimin Wang, andKam-Fai Wong.
Machine Intelligence Research (2023).

Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue
Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, and Kam-Fai Wong.
Findings of EMNLP 2023 (long papers).

ReadPrompt: A Readable Prompting Method for Reliable Knowledge Probing
Zezhong Wang, Luyao Ye, Hongru Wang, Wai-Chung Kwan, David Ho, and Kam-Fai Wong.
Findings of EMNLP 2023 (long papers).

MCML: A novel Memory-based Contrastive Meta-Learning method for Few Shot Slot Tagging
Hongru Wang, Zezhong Wang, Wai-Chung Kwan, and Kam-Fai Wong.
AACL 2023 (long papers).

Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization
Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, and Kam-Fai Wong.
Findings of ACL 2023 (long papers).

Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
Zezhong Wang, Hongru Wang, Wai-Chung Kwan, Jia Zhu, Gabriel Pui Cheong Fung, and Kam-Fai Wong.
ICNLSP 2022 (long papers).

Using time-series patterns in word segmentation for data preprocessing: A methodological development in evolving public discourse mining
Yin Zhang, Wai-Chung Kwan, Wai-Yeung Ho, Chi-Chiu Tong, and Tsz-Ho Hui.
Conference of International Communication Association (2020).

Experience

• Jun.2023 - Feb.2024. Research Intern, Huawei Noah’s Ark Lab, Hong Kong.
• Aug. 2019 - Aug. 2020. Research Assistant, Hong Kong Baptist University, Hong Kong.
• May. 2018 - Aug. 2018. Data Scientist Intern, MultiMedia Big Data Analytics Limited, Hong Kong.
• Jan. 2019 - May. 2019. Research Assistant, Hong Kong Baptist University, Hong Kong.

Miscellany

In my free time, I enjoy reading books related to science, especially neuroscience. I also like watching movies and visiting art galleries. I used to play badminton and drums regularly before my PhD journey. Hopefully, I can pick them up again shortly.