I am currently an associate professor at the School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen). Before joining HITsz, I received my PhD degree (working on semantic-based dialogue modeling) from Zhejiang University in Mar 2023, where I was honored to be advised by Yue Zhang. I earned my master degree (working on unsupervised word translation) from Harbin Institute of Technology, supervised by Tiejun Zhao and Hailong Cao. I obtained my undergraduate degree on Computer Science and Technology from Harbin Institute of Technology.

My research area spans from large language models (LLMs) and structured learning. I am currently focusing on developing technical solutions to achieve deep reasoning with LLMs in an efficient and generalizable manner, as well as reasoning on structured data (Knowledge Graphs, Semantic Graphs, Tables, Protein Structures). Beyond this, I maintain a strong interest in fundamental NLP tasks (syntax and semantics) as well as real-world NLP applications (dialogue systems and machine translation).

Recruit: I am currently looking for self-motivated undergraduate students, interns, and prospective Master's (2027) or PhD (2027) candidates to doing research with me. If you have a strong interest in LLMs or structures, I’d love to hear from you! Please feel free to reach out via email or visit me at L1910 to discuss potential opportunities.

🔥 News

• 2026.03:  🎉🎉 We will host the second share task on Classical Chinese Poetry Appreciation at CCL 2026.
• 2026.01:  🎉🎉 Two papers are accepted at ICLR2026.
• 2025.09:  🎉🎉 Two papers are accepted at NeurIPS2025.
• 2025.08:  🎉🎉 Two papers are accepted at EMNLP2025, both are main conference.
• 2025.07:  🎉🎉 Won the championship at the CAMRP2025 evaluation task.
• 2025.05:  🎉🎉 Five papers are accepted at ACL2025, three main conference and two findings.
• 2025.05:  🎉🎉 One paper is accepted at ICML2025.
• 2025.04:  🎉🎉 One paper is accepted at IJCAI2025.
• 2025.04:  🎉🎉 We will host a Shared Task on Classical Chinese Poetry Appreciation at CCL 2025. We welcome wide participation.
• 2024.09:  🎉🎉 One paper is accepted at EMNLP2024.
• 2024.07:  🎉🎉 One paper is accepted at CoLM2024.
• 2024.05:  🎉🎉 Two papers are accepted at ACL2024, one main conference and one findings.
• 2023.05:  🎉🎉 Two papers are accepted at ACL2023, one main conference and one findings.

📝 Selected Publications

Please go to Google Scholar for a complete list of publications.

[Recent work on LLMs]

• ICLR 2026 Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment [code]
  Hongbin Zhang, Kehai Chen, Xuefeng Bai^✉, Yang Xiang^✉, Min Zhang.
• ICLR 2026 Culture In a Frame: C³B as a Comic-Based Benchmark for Multimodal Culturally Awareness [code]
  Yuchen Song, Andong Chen, Wenxin Zhu, Kehai Chen, Xuefeng Bai^✉, Muyun Yang, Tiejun Zhao^✉.
• NeurIPS 2025 Exploring Translation Mechanism of Large Language Models [code]
  Hongbin Zhang, Kehai Chen, Xuefeng Bai, Xiucheng Li, Yang Xiang, Min Zhang.
• NeurIPS 2025 XIFBench: Evaluating Large Language Models on Multilingual Instruction Following [code]
  Zhenyu Li, Xuefeng Bai^✉, Yunfei Long, Kehai Chen, Yaoyin Zhang, Xuchen Wei, Juntao Li, Min Zhang.
• EMNLP 2025 Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent [code]
  Xingzuo Li, Kehai Chen, Yunfei Long, Xuefeng Bai^✉, Yong Xu, Min Zhang.
• EMNLP 2025 Benchmarking LLMs for Translating Classical Chinese Poetry: Evaluating Adequacy, Fluency, and Elegance [code]
  Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai^✉, Yang Xiang, Muyun Yang, Tiejun Zhao, Min Zhang.
• ICML 2025 Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin [code]
  Yuchen Wang, Xuefeng Bai^✉, Xiucheng Li, Weili Guan, Liqiang Nie and Xinyang Chen^✉.
• IJCAI 2025 A Survey on the Feedback Mechanism of LLM-based AI Agents [code]
  Zhipeng Liu, Xuefeng Bai^✉, Kehai Chen, Xinyang Chen, Xiucheng Li, Yang Xiang, Jin Liu, Hong-Dong Li, Yaowei Wang, Liqiang Nie and Min Zhang.
• ACL 2025 Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling [code] Qiyuan Deng, Xuefeng Bai^✉, Kehai Chen, Yaowei Wang, Liqiang Nie, Min Zhang.
• ACL 2025 Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning [code]
  Yingjie Zhu, Xuefeng Bai^✉, Kehai Chen, Yang Xiang, Jun Yu, Min Zhang
• ACL 2025 Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation [code]
  Andong Chen, Song Yuchen, Kehai Chen, Xuefeng Bai, Muyun Yang, Liqiang Nie, Jie Liu, Tiejun Zhao, Min zhang.
• ACL 2025 (Findings) The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents [[code] (to-be-public)] Yihong Tang, Kehai Chen, Xuefeng Bai, Zheng-Yu Niu, Bo Wang, Jie Liu, Min Zhang.
• ACL 2025 (Findings) LLM-based Translation Inference with Iterative Bilingual Understanding [code]
  Andong Chen, Kehai Chen, Yang Xiang, Xuefeng Bai, Muyun Yang, Yang Feng, Tiejun Zhao, Min zhang.
• EMNLP 2024 (Findings) Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering [code]
  Yu Zhang, Kehai Chen, Xuefeng Bai, Zhao Kang, Quanjiang Guo and Min Zhang.
• CoLM 2024 See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses
  Yulong Chen, Yang Liu, Jianhao Yan, Xuefeng Bai, Ming Zhong, Yinghao Yang, Ziyi Yang, Chenguang Zhu, Yang Liu and Yue Zhang.

• ACL 2024 (Findings) Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Models [code]
  Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang and Min Zhang.

• ACL 2024 DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms [code]
  Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai, Yang Xiang, Muyun Yang, Tiejun Zhao and Min Zhang.

[Representative work on Fundamental NLP]

• TASLP 2025 Constituency Parsing using LLMs [code] Xuefeng Bai, Jialong Wu, Yulong Chen, Zhongqing Wang, Kehai Chen, Min Zhang and Yue Zhang.
• ACL 2022 Graph-pretraining for AMR Parsing and Generation [code]
  Xuefeng Bai, Yulong Chen and Yue Zhang.
• ACL 2021 Semantic Representation for Dialogue Modeling[code]
  Xuefeng Bai, Yulong Chen, Linfeng Song and Yue Zhang.
• EMNLP 2022 Cross-domain Generalization for AMR Parsing [code]
  Xuefeng Bai, Sen Yang, Leyang Cui, Linfeng Song and Yue Zhang.
• COLING 2022 Semantic-based Pre-training for Dialogue Understanding[code]
  Xuefeng Bai, Yulong Chen, Linfeng Song and Yue Zhang.
• EMNLP 2020 Online back-parsing for AMR-to-text Generation [code]
  Xuefeng Bai, Linfeng Song and Yue Zhang.

📚 Teaching

• COMP6023: Mathematical Methods in Image Processing
  • Graduate, HITsz, Spring (2024, 2025)
• COMP1011: Principles and Practice of Programming
  • Undergraduate, HITsz, Fall (2024, 2025)

📝 Academic Services

• Area Chair / Action Editor
  • ARR Rolling Review (2024-now)
  • EMNLP (2022, 2024)
  • NAACL 2025
  • ACL 2025
  • CCL 2024
• Program Committee Member:
  • ARR, ACL, EMNLP, NAACL, COLING, AACL, CCL, NLPCC, etc.

• Journal Reviewer:

  • TACL, Machine Learning, ACM/IEEE TASLP, KBS, ACM TALLIP, etc.

🎖 Honors and Awards

• 2023.03 Outstanding graduate of Zhejiang Province.
• 2023.03 Outstanding graduate of Zhejiang University.
• 2021.10 National Scholarship for doctoral students.
• 2019.06 Top100 Master Thesis in Harbin Institute of Technology.
• 2018.09 National Scholarship for master students.
• 2017.06 Top100 graduation projects in Harbin Institute of Technology.

💻 Internships

• 2021.09 - 2023.03, AILab, Tencent, advised by Dr. Linfeng Song.
• 2020.02 - 2020.06, DAMO Academy, Alibaba, advised by Dr. Boxing Chen.
• 2018.07 - 2018.10, MT Group, Sogou Inc, advised by Dr. Feifei Zhai.