About me

I am a third-year PhD student (2021 - present) of Department of Computer Science and Engineering at Shanghai Jiao Tong University (SJTU). I am fortunate to be advised by Prof. Rui Wang. Before that, I received the bachelor degree in Software Engineering from South China University of Technology (SCUT). I am currently a research intern at Tencent AI Lab, co-advised by Dr. Xing Wang and Dr. Zhaopeng Tu. I also work closely with Zhuosheng Zhang.

🔬 Research

Autonomous Agent powered by Large Language Models

  • Multi-agent debate [Pre-print]
  • Evaluating and improving agent safety [Pre-print]

Multilinguality & Machine Translation

  • Bridging the gap between training signal and real user input [ACL 2022]
  • Human-like translation strategy [TACL 2024]
  • Improving translation with human feedback [NAACL 2024]
  • Cross-lingual consistency for text watermark [ACL 2024 (Oral)]

🔥 News

  • 2024.06: 🇲🇽🌮 I am attending NAACL 2024 @ Mexico. It’s been a wonderful journey.
  • 2024.05: 🎉🎉 One paper about cross-lingual text watermark is accepted by ACL 2024.
  • 2024.03: 🎉🎉 One paper about improving translation with human feedback is accepted by NAACL 2024.
  • 2023.11: 🎉🎉 One paper about human-like translation strategy is accepted by TACL 2024.
  • 2023.05: We introduce the MAPS framework, enabling LLMs to mimic the human translation strategy. See also the media coverage 📸.
  • 2023.05: We propose multi-agent debate framework (MAD) with large language models (preprint).

🖨️ Selected preprints

* denotes co-first authors

arXiv 2024
yuan2024rjudge

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Tongxin Yuan*, Zhiwei He*, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu

  • Are LLM agents aware of safety risks in real-world applications? Let’s find out with R-Judge!
arXiv 2023
liang2023encouraging

Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Tian Liang*, Zhiwei He*, Wenxiang Jiao*, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, Shuming Shi

  • We propose a multi-agent debate framework with large language models.

📝 Selected publications

* denotes co-first authors

ACL 2024 (Oral)
he2024can

Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models

Zhiwei He*, Binglin Zhou*, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, Rui Wang

  • Text watermarks can be easily removed by translation.
  • We analyze and improve the cross-lingual consistency of text watermarks.
NAACL 2024
he2024improving

Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model

Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, Zhaopeng Tu

  • We identify the overoptimization problem when using QE-based reward models for training translation model.
  • We address it with a simple yet effective method.

🎖 Honors and Awards

  • 2022.8: 1st place in the WMT22 General Translation Task, English to Livonian (Unconstrained System).
  • 2022.8: 2nd place in the WMT22 General Translation Task, Livonian to English (Unconstrained System).
  • 2018, 2019: First Class Scholarship.

💬 Invited Talks

  • 2024.07: Can Watermarks Survive Translation, AITIME | [video] [slide]
  • 2023.11: Improving Machine Translation with Human Strategy and Feedback, CJNLP | [slide]
  • 2022.08: Unsupervised Neural Machine Translation, CCKS 2022

💻 Internships