Chen Zhang (张晨)
Email: zhangch [AT] pku [DOT] edu [DOT] cn

I am a fourth-year Ph.D. student at PIE Lab, Wangxuan Institute of Computer Technology, Peking University, advised by Prof. Yansong Feng and Prof. Dongyan Zhao.

I received my B.Sc. degree from School of Electronic Engineering and Computer Science at Peking University in 2021.

[CV] [Google Scholar] [Github] [X]

  Research Interests

Currently, my research interests include

  • NLP for Low-Resource Languages: Enhancing the transparency, inclusivity, and efficiency in human language technology for underrepresented languages.
  • Complex Reasoning with LLMs: Harnessing the potential of LLMs to tackle complex problems and building reliable systems for specialized domains such as law.

Previously, I worked on question answering, focusing on reading comprehension and knowledge base QA.

  News
  • [SEP 2024] Our paper on applying model merging to low-resource languages is accepted to EMNLP 2024.
  • [MAY 2024] Our papers on low-resource languages and MoE are accepted to ACL 2024.
  • [MAR 2024] Check out our new work on adapting LLMs to unseen languages through prompting. [arxiv]
  • [NOV 2023] We release MC2, the largest corpus of minority langugaes in China. [github] [arxiv]
  Publications & Preprints
      (* Equal Contribution)

1. Low-Resource Languages & Multilinguality

Unlocking the Potential of Model Merging for Low-Resource Languages
EMNLP 2024 (Findings)
Mingxu Tao*, Chen Zhang*, Quzhe Huang*, Tianyao Ma, Songfang Huang, Dongyan Zhao, Yansong Feng
[preprint]

Teaching Large Language Models an Unseen Language on the Fly
ACL 2024 (Findings)
Chen Zhang, Xiao Liu, Jiuheng Lin, Yansong Feng
[paper] [github] [website]

MC2: Towards Transparent and Culturally-Aware NLP for Minority Languages in China
ACL 2024
Chen Zhang*, Mingxu Tao*, Quzhe Huang*, Jiuheng Lin*, Zhibin Chen, Yansong Feng
[paper] [github] [website]

Can LLMs Learn a New Language on the Fly? A Case Study on Zhuang
ICLR 2024 Tiny Paper
Chen Zhang, Mingxu Tao, Quzhe Huang, Zhibin Chen, Yansong Feng
[paper]

Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension
EACL 2023 (Findings)
Chen Zhang, Yuxuan Lai, Yansong Feng, Xingyu Shen, Haowei Du, Dongyan Zhao
[paper] [github]

2. Complex Reasoning with LLMs

Harder Task Needs More Experts: Dynamic Routing in MoE Models
ACL 2024
Quzhe Huang*, Zhenwei An*, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng
[paper]

Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?
ICLR 2024 Tiny Paper
Yutong Hu, Quzhe Huang, Mingxu Tao, Chen Zhang, Yansong Feng
[paper]

Lawyer LLaMA: Enhancing LLMs with Legal Knowledge
Arxiv
Quzhe Huang*, Mingxu Tao*, Chen Zhang*, Zhenwei An*, Cong Jiang, Zhibin Chen, Zirui Wu, Yansong Feng
[arxiv] [github]

The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
ACL 2023 (Findings)
Xiao Liu, Da Yin, Chen Zhang, Yansong Feng, Dongyan Zhao
[paper] [github]

3. Question Answering

Relation-Aware Question Answering for Heterogeneous Knowledge Graphs
EMNLP 2023 (Findings)
Haowei Du, Quzhe Huang, Chen Li, Chen Zhang, Yang Li, Dongyan Zhao
[paper]

How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension
ACL 2023 (Findings)
Chen Zhang, Jiuheng Lin, Xiao Liu, Yuxuan Lai, Yansong Feng, Dongyan Zhao
[paper] [github]

UnifEE: Unified Evidence Extraction for Fact Verification
EACL 2023
Nan Hu, Zirui Wu, Yuxuan Lai, Chen Zhang, Yansong Feng
[paper] [github]

Knowledge-Enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering
NLPCC 2022
Haowei Du, Quzhe Huang, Chen Zhang, Dongyan Zhao
[paper] [preprint]

Extract, Integrate, Compete: Towards Verification Style Reading Comprehension
EMNLP 2021 (Findings)
Chen Zhang, Yuxuan Lai, Yansong Feng, Dongyan Zhao
[paper] [github]

A review of deep learning in question answering over knowledge bases
AI Open 2021, Volume 2
Chen Zhang, Yuxuan Lai, Yansong Feng, Dongyan Zhao
[paper]

Why Machine Reading Comprehension Models Learn Shortcuts?
ACL-IJCNLP 2021 (Findings)
Yuxuan Lai, Chen Zhang, Yansong Feng, Quzhe Huang, Dongyan Zhao
[paper] [github]

  Talks
  • Long Documents Meet LLMs, December 2023, Sichuan University & Chinese Information Processing Society of China, with Quzhe Huang and Mingxu Tao. [slides]
  Teaching & Services
   Teaching Assistant
  • Foundations of Natural Language Processing, Peking University, Spring 2024
  • Empirical Methods for Natural Language Processing, Peking University, Spring 2022
  • Data Structures and Algorithms, Peking University, Fall 2020 & Spring 2021
   Program Committee
  • Reviewer: ACL Rolling Review (since November 2021), ACL (since 2023), EMNLP (since 2022), COLING (since 2022)
   Volunteer
  • ACL 2024, On-site Volunteer
  • EMNLP 2021, Remote Volunteer
  Honors & Awards
  • Award for Scientific Research, Peking University, 2024
  • Outstanding Graduates of Beijing Ordinary Colleges and Universities, Beijing Municipal Education Commission, 2021
  • Excellent Graduate, Peking University, 2021
  • Best Project, Google ML Winter Camp, 2020 [link]
  • Meritorious Winner, Mathematical Contest In Modeling (MCM), 2019
  • Merit Student, Peking University, 2018 & 2019
  • Founder Scholarship, 2018 & 2019
  Contact

Wangxuan Institute of Computer Technology, Peking University
No. 128 Zhongguancun North Street
Haidian District, Beijing, 100871
zhangch [at] pku.edu.cn


  Miscellaneous
  • My name written in Chinese characters is 张晨. 晨 means morning in Chinese.
  • My mother tongue is Jinsha Dialect (金沙话), a transitional dialect between Mandarin and Wu Chinese.
  • Besides Chinese and English, I can speak Japanese (intermediate), Spanish (basic) and German (basic).

Website design: