About me

I am a forth-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

Large and Efficient Reasoning Models

• DeepMath-103K [Preprint]
• Underthinking issue in o1-like models [Preprint]
• Overthinking issue in o1-like models [ICML 2025]
• Rank-sharing LoRA [ICLR 2025]

Autonomous Agent powered by Large Language Models

• Multi-agent debate [EMNLP 2024]
• Evaluating and improving agent safety [EMNLP 2024 (Findings)]

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

• 2025.05: 🎉🎉 One paper about model overthinking accepted by ICML 2025.
• 2025.04: 🇸🇬🇸🇬 Attended ICLR 2025 @ Singapore.
• 2025.04: 🎓🎓 Released DeepMath-103K, a large-scale, challenging, decontaminated, and verifiable math dataset for advancing reasoning.
• 2025.01: 🤯🤯 Revealed underthinking issue in o1-like models (preprint).
• 2024.12: 🎉🎉 One paper about parameter-efficient fine-tuning accepted by ICLR 2025.
• 2024.12: 🤯🤯 Revealed overthinking issue in o1-like models (preprint).
• 2024.08: 🇹🇭🐘 Gave an oral presentation at ACL 2024 on cross-lingual text watermark.
• 2024.06: 🇲🇽🌮 Attended NAACL 2024 @ Mexico.
• 2024.05: 🎉🎉 One paper about cross-lingual text watermark accepted by ACL 2024.
• 2024.03: 🎉🎉 One paper about improving translation with human feedback accepted by NAACL 2024.
• 2023.11: 🎉🎉 One paper about human-like translation strategy accepted by TACL 2024.
• 2023.05: Introduced the MAPS framework, enabling LLMs to mimic the human translation strategy. See also the media coverage 📸.
• 2023.05: Proposed a multi-agent debate framework (MAD) with large language models (EMNLP 2024).

🖨️ Selected preprints

* denotes co-first authors

arXiv 2025

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Zhiwei He*, Tian Liang*, Jiahao Xu*, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu

CODE BIB DATA SLIDE

• 💪🏻 Challenging math dataset with verifiable answers.
• 🔥 Top trending dataset on HuggingFace (30,000+ downloads).
• 📈 SOTA on math reasoning benchmarks.

• Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

  Yue Wang*, Qiuzhi Liu*, Jiahao Xu*, Tian Liang*, Xingyu Chen*, Zhiwei He*, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu

  arXiv 2025 | BIB
  
  

📝 Selected publications

* denotes co-first authors

• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

  Xingyu Chen*, Jiahao Xu*, Tian Liang*, Zhiwei He*, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu

  ICML 2025 | BIB

  • Reasoning models ofter overthinks, which contribute minimally to improving accuracy.
    
    

• RaSA: Rank-Sharing Low-Rank Adaptation

  Zhiwei He, Zhaopeng Tu, Xing Wang, Xingyu Chen, Zhijie Wang, Jiahao Xu, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang

  ICLR 2025 | CODE BIB POSTER SLIDE

  • We show how sharing ranks across layers significantly improves LoRA’s expressive capacity for efficient LLM adaptation.
    
    

• 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

  EMNLP 2024 (Findings) | PROJ BIB HOME POSTER

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

• 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

  EMNLP 2024 | CODE BIB POSTER SLIDE

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

• 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

  ACL 2024 | CODE BIB HOME POSTER SLIDE

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

• 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

  NAACL 2024 | CODE BIB POSTER SLIDE

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

• 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

  TACL 2024 | CODE BIB POSTER SLIDE

  • 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
    
    

• Tencent AI Lab-Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task

  Zhiwei He, Xing Wang, Zhaopeng Tu, Shuming Shi, Rui Wang

  WMT 2022 | CODE BIB POSTER

  • Machine translation system for Livonian
  • 🥇1st place for English$\Rightarrow$Livonian (unconstrained system)
  • 🥈2nd place for Livonian$\Rightarrow$English (unconstrained system)
    
    

• Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

  Zhiwei He, Xing Wang, Rui Wang, Shuming Shi, Zhaopeng Tu

  ACL 2022 | CODE BIB POSTER SLIDE

🎖 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

• 2025.05: RaSA: Rank-Sharing Low-Rank Adaptation, 腾讯混元ICLR前沿论文分享 | [slide]
• 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

• 2021 - present: Tencent AI Lab, Shenzhen, Mentors: Dr. Xing Wang and Dr. Zhaopeng Tu.