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 Tencen AI Lab, co-advised by Dr. Xing Wang and Dr. Zhaopeng Tu.

πŸ”¬ Research

Autonomous Agent powered by Large Language Models

  • Multi-agent debate [Preprint]

Human-centered 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

πŸ”₯ News

  • 2023.11: πŸŽ‰πŸŽ‰ 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 πŸ“Έ and demo.
  • 2023.05: We propose multi-agent debate framework (MAD) with large language models (preprint).
  • 2023.05: One short paper about tense consistency of machine translation is accepted by ACL 2023.

πŸ–¨οΈ Preprints

* denotes co-first authors

arXiv 2023
zhang2023igniting

Igniting Language Intelligence: The Hitchhiker’s Guide From Chain-of-Thought Reasoning to Language Agents

Zhuosheng Zhang, Yao Yao, Aston Zhang, Xiangru Tang, Xinbei Ma, Zhiwei He, Yiming Wang, Mark Gerstein, Rui Wang, Gongshen Liu, Hai Zhao

  • A journey from CoT to language agent.
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

  • Yes. Multi-agent debate.

πŸ“ Publications

* denotes co-first authors

TACL 2024
he2023exploring

Exploring Human-Like Translation Strategy with Large Language Models

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

  • We propose MAPS, the first machine translation system that mimics human translation strategies.
  • Outperforms WMT22 winners in 5 out of 11 translation directions.
  • Media coverage

πŸŽ– 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.

πŸ’¬ Invited Talks

  • 2023.11: Improving Machine Translation with Human Strategy and Feedback, CJNLP | [slide]
  • 2022.08: Unsupervised Neural Machine Translation, CCKS 2022

πŸ’» Internships