I am a final-year PhD student at CUHK text mining group, supervised by Prof. Lam Wai. Prior to this, I obtained my master degree at Harbin Institute of Technology.

In the past, my research primarily revolved around enhancing the generalization capabilities and robustness of natural language processing (NLP) models. This was achieved through the optimization of model architecture, learning algorithms, and data representation. Currently, my interests have shifted towards large language model (LLM) reasoning and alignment.

📝 Preprints

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning

Chang Gao, Wenxuan Zhang, Guizhen Chen, Wai Lam

Paper Code

📝 Publications

NeurIPS 2024

StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving

Chang Gao, Haiyun Jiang, Deng Cai, Shuming Shi, Wai Lam

Paper Code

ACL 2024 Findings

CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Qibing Ren*, Chang Gao*, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma

Paper Code

NeurIPS 2023

M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

Wenxuan Zhang, Sharifah Mahani Aljunied, Chang Gao, Yew Ken Chia, Lidong Bing

Paper Code

ACL 2023 Findings

Easy-to-Hard Learning for Information Extraction

Chang Gao, Wenxuan Zhang, Wai Lam, Lidong Bing

Paper Code

EMNLP 2022 Findings

Towards Generalizable and Robust Text-to-SQL Parsing

Chang Gao, Bowen Li, Wenxuan Zhang, Wai Lam, Binhua Li, Fei Huang, Luo Si, Yongbin Li

Paper Code

EMNLP 2022

Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue

Yingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao, Jian Sun, Nevin L. Zhang

Paper Code

ACL 2022

UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

Chang Gao, Wenxuan Zhang, Wai Lam

Paper Code

ECIR 2022

Search Clarification Selection via Query-Intent-Clarification Graph Attention

Chang Gao, Wai Lam

Paper

CIKM 2020

Rotate3D: Representing Relations as Rotations in Three-Dimensional Space for Knowledge Graph Embedding

Chang Gao, Chengjie Sun, Lili Shan, Lei Lin, Mingjiang Wang

Paper Code

📖 Educations

  • 2020.08 - 2025.03 (now), PhD, The Chinese University of Hong Kong, Hong Kong, China
  • 2018.09 - 2020.06, Master, Harbin Institute of Technology, Harbin, China
  • 2014.09 - 2018.06, Undergraduate, Harbin Institute of Technology, Weihai, China

🎖 Honors and Awards

  • 2020.09 ACM SIGIR Student Travel Grant
  • 2020.06 Outstanding Master Thesis Award
  • 2018.06 Outstanding Graduate Award
  • 2017.11 National Scholarship
  • 2016.11 National Scholarship