Chujie Zheng 郑楚杰

Welcome! I am Chujie Zheng (“Chujie” pronounced similarly to “Cho-Jay”), a fourth-year Ph.D candidate in CoAI Group at Tsinghua University, fortunately advised by Prof. Minlie Huang. I am also currently a visiting scholar in PlusLab at UCLA, fortunately hosted by Prof. Nanyun (Violet) Peng. I received my B.Sc degree from Dept. of Physics, Tsinghua University. You can find my CV here (updated: 04/2024).

I have a broad research interest in building trustworthy AI systems, with the current focus on LLM alignment (preprint, ICLR 2024 Spotlight, SeT LLM @ ICLR 2024, ACL 2023 Findings). My ultimate research goal is to advance and oversee AI systems in a scalable way (with minimal human intervention) and ensure they operate transparently and responsibly.

Previously, I conducted research on LLMs for social good, with a main focus on building LLMs for emotional support (ACL 2021, ACL 2023 Findings). I have also built a series of popular NLP datasets, including ChID, KDConv, ESConv, and CDConv, and am proud of them stimulating follow-up work!

News

• [Pinned: Collaboration] If you would like my collaboration for your research projects, feel free to reach out! Besides the aforementioned research interest, I am also open to exploring unconventional or under-defined research problems!
• [04/2024] Arxived our paper on LLM alignment via model extrapolation (ExPO) [paper]
• [03/2024] Our DRO paper is accpeted for Oral presentation at the SeT LLM workshop @ ICLR 2024 [paper]. See you in Vienna 🇦🇹!
• [02/2024] Released a GitHub repository of chat templates for HuggingFace LLMs [repo]. Try it!
• [01/2024] Arxived our paper on safety prompt optimization (DRO) for safeguarding LLMs [paper]
• [01/2024] Our PriDe paper is accpeted for Spotlight presentation (5%) at ICLR 2024 [openreview]. See you in Vienna 🇦🇹!
• [11/2023] Started my visiting research at UCLA, hosted by Nanyun Peng
• [09/2023] Arxived our paper on debiasing LLMs (PriDe) in MCQ evaluation [paper]

Selected Projects

1. Weak-to-Strong Extrapolation Expedites Alignment
   Chujie Zheng, Ziqi Wang, Heng Ji, Minlie Huang, Nanyun Peng
   arXiv:2404.16792
   [paper] [repo]
2. On Prompt-Driven Safeguarding for Large Language Models
   Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, Nanyun Peng
   Secure and Trustworthy LLM Workshop @ ICLR 2024 (Oral)
   [paper] [repo]
3. Chat Templates for HuggingFace Large Language Models
   Chujie Zheng
   GitHub Repository (170+ Stars)
   [repo]
4. Large Language Models Are Not Robust Multiple Choice Selectors
   Chujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou, Minlie Huang
   ICLR 2024 (Spotlight: 5%)
   [paper] [repo]
5. Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning
   Chujie Zheng, Pei Ke, Zheng Zhang, Minlie Huang
   ACL 2023 Findings
   [paper] [repo]
6. AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation
   Chujie Zheng, Sahand Sabour, Jiaxin Wen, Zheng Zhang, Minlie Huang
   ACL 2023 Findings
   [paper] [repo]
7. Towards Emotional Support Dialog Systems
   Siyang Liu*, Chujie Zheng*, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, Minlie Huang (*: Equal contribution)
   ACL 2021
   [paper] [repo]

You can find my full paper list on Google Scholar or from this page.

Education

• Aug 2020 - present. Ph.D student in CoAI Group, Department of Computer Science and Technology, Tsinghua University. Advisor: Minlie Huang
• Nov 2023 - present. Visiting Scholar in PlusLab, Computer Science Department, UCLA. Advisor: Nanyun (Violet) Peng
• Aug 2016 - Jul 2020. B.Sc. in Physics, Tsinghua University. Major GPA: 3.98/4.00 (ranking 2/59)

Services

• Area Chair: ACL (24), ACL Rolling Review (24)
• Reviewer: ACL (22/23), EMNLP (21/22), NAACL (24), EACL (23), ACL Rolling Review (21/22/23), CogSci (24), AAAI (22/23)

Awards and Honors

• Schlumberger Scholarship, Tsinghua University, 2023
• Comprehensive Merit Scholarship, Tsinghua University, 2022/2021
• Chi-Sun YEH (叶企孙) Scholarship (Top 5/100), Department of Physics, Tsinghua University, 2020
• Outstanding Undergraduate, Tsinghua University, 2020
• China National Scholarship (Top 2/100), 2019
• Comprehensive Merit Scholarship, Tsinghua University, 2018

Talks

• Nov 2022, Shanghai AI Lab. Towards Well-behaved Dialogue Systems.
• Jul 2021, AI Time. Approaches of Empathy Expression and Emotional Support in Dialogue Systems. [video]
• Nov 2020, Biendata & PaperWeekly. Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation. [video]
• Jul 2020, AI Time. KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation. [video]