Publications

18. Format as Nuisance: Intervention-Inspired Cross-Format Distillation for Knowledge Conflicts. Yue Yu, Wang Luo, Shenghao Ye, Zepeng Bao, Jiacheng Liu, Yongqi Li, Wenxin Tang, Tieyun Qian. EMNLP 2026.

17. Developing Continuous Toxicity Detection Against Increasing Types of Perturbed Toxic Text. Hankun Kang, Jianhao Chen, Yongqi Li, Xin Miao, Mayi Xu, Shen Zhou, Ming Zhong, Yuanyuan Zhu, Tieyun Qian*. Information Processing & Management.

16. Debiasing LLMs in Knowledge-Intensive Tasks via Information-Gain Guided Front-Door Adjustment. Xin Miao, Yongqi Li, Hankun Kang, Mayi Xu, Jintao Wen, Yuanyuan Zhu, Ming Zhong, Jiawei Jiang, Tieyun Qian*. DASFAA 2026.

15. How Robust are Large Language Models Against Word-Level Spurious Correlations? A Causal Discovery Approach. Xin Miao, Yongqi Li, Hankun Kang, Mayi Xu, Jintao Wen, Yuyang Ren, Tieyun Qian*. Machine Learning.

14. Recursive Short-to-Long Generalization for Multi-hop Reasoning. Mayi Xu, Ke Sun, Jianhao Chen, Qiankun Pi, Guixin Su, Yunfeng Ning, Yongqi Li, Yuanyuan Zhu, Ming Zhong, Jiawei Jiang, Tieyun Qian*. SIGIR 2026.

13. Understanding Generalization in Role-Playing Models via Information Theory. Yongqi Li†, Hao Lang†, Fei Huang, Tieyun Qian*, Yongbin Li*. ACL 2026 Findings.

12. Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions. Yongqi Li†, Hao Lang†, Tieyun Qian*, Yongbin Li*. ACL 2026.

11. A Survey on Training-free Alignment of Large Language Models. Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian*. EMNLP 2025 Findings.

10. Enhancing Relation Extraction via Supervised Rationale Verification and Feedback. Yongqi Li, Xin Miao, Shen Zhou, Mayi Xu, Yuyang Ren, Tieyun Qian*. AAAI 2025 (Oral, 4.6%).

9. Strong Empowered and Aligned Weak Mastered Annotation for Weak-to-Strong Generalization. Yongqi Li, Xin Miao, Mayi Xu, Tieyun Qian*. AAAI 2025.

8. Aligning VLM Assistants with Personalized Situated Cognition. Yongqi Li, Shen Zhou, Xiaohu Li, Xin Miao, Jintao Wen, Mayi Xu, Jianhao Chen, Birong Pan, Hankun Kang, Yuanyuan Zhu*, Ming Zhong, Tieyun Qian*. ACL 2025.

7. Prompting Large Language Models for Counterfactual Generation: An Empirical Study. Yongqi Li†, Mayi Xu†, Xin Miao†, Shen Zhou†, Tieyun Qian*. LREC-COLING 2024.

6. An Ensemble-of-Experts Framework for Rehearsal-free Continual Relation Extraction. Shen Zhou, Yongqi Li, Xin Miao, Tieyun Qian*. ACL 2024 Findings.

5. Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction. Xin Miao, Yongqi Li, Shen Zhou, Tieyun Qian*. ACL 2024 Findings.

4. Adaption-of-Thought: Learning Question Difficulty Improves Large Language Models for Reasoning. Mayi Xu, Yongqi Li, Ke Sun, Tieyun Qian*. EMNLP 2024.

3. Cold-start Multi-hop Reasoning by Hierarchical Guidance and Self-verification. Mayi Xu, Ke Sun, Yongqi Li, Tieyun Qian*. ECML/PKDD 2023.

2. Generating Commonsense Counterfactuals for Stable Relation Extraction. Xin Miao, Yongqi Li, Tieyun Qian*. EMNLP 2023.

1. Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition. Yongqi Li, Yu Yu, Tieyun Qian*. EMNLP 2023 Findings.