📝 Selected Publications

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

[Recent work on LLMs]

• ICML 2026 (splotlight) Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance [code]
  Yingjie Zhu, Xuefeng Bai^✉, Kehai Chen, Yang Xiang, Youcheng Pan, Xiaoqiang Zhou, Min Zhang.
• ICML 2026 Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [code]
  Zirui Li, Xuefeng Bai^✉, Kehai Chen, Yizhi Li, Jian Yang, Chenghua Lin, Min Zhang.
• ICML 2026 Evaluating and Steering Modality Preferences in Multi-modal LLMs [code]
  Yu Zhang, Jinlong Ma, Yongshuai Hou, Xuefeng Bai^✉, Kehai Chen, Yang Xiang, Jun Yu, Min Zhang.
• ICML 2026 Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck [code]
  Hongbin Zhang, Kehai Chen, Xuefeng Bai, Youcheng Pan, Yang Xiang, Jinpeng Wang, Min Zhang.
• ICML 2026 The Secret Engine Behind RLHF: It’s Contarstive Learning All Along [code]
  Xufei Lv, Kehai Chen, Haoyuan Sun, Xuefeng Bai, Min Zhang, Houde Liu.
• ACL 2026 SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking [code]
  Weiyang Huang, Xuefeng Bai^✉, Kehai Chen, Xinyang Chen, Yibin Chen, Weili Guan, Min Zhang.
• ACL 2026 (Findings) Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition [code]
  Jinlong Ma, Yu Zhang, Xuefeng Bai^✉, Kehai Chen, Yuwei Wang, Zeming Liu^✉, Jun Yu, Min Zhang.
• 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.