Yongqi Li
Email: liyongqi[at]whu.edu.cn
About
Hi! I am a final-year Master student at NLPGM Lab @ Wuhan University, under the supervision of Prof. Tieyun Qian. I obtained my B.Eng. with an honor from Wuhan University in 2023.
My current research focuses on exploring methods to (theoretically) understand and (empirically) improve the generalization of AI Alignment.
I am committed to developing trustworthy AI that can communicate effectively with humans.
Follow
Experience
- Research Intern, Tongyi Lab, Alibaba, May 2025 - Jan. 2026.
Awards & Honors
- National Scholarship, Ministry of Education, 2025
- Outstanding Undergraduate Thesis (top 5%), Wuhan University, 2023
- Honor Graduate, Hongyi Honor College, Wuhan University, 2023
- Huawei Scholarship, The Joint Working Group of the Ministry of Education and Huawei, 2022
Publications
(*=corresponding author, †=Equal Contribution)
2025
Aligning VLM Assistants with Personalized Situated Cognition. [Paper] [Code] [Review] [CIPS-SMP 2025 Spotlight Poster]
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 The 63rd Annual Meeting of the Association for Computational Linguistics
Strong Empowered and Aligned Weak Mastered Annotation for Weak-to-Strong Generalization. [Paper] [Code] [Review] [Blog (中文)]
Yongqi Li, Xin Miao, Mayi Xu, Tieyun Qian*.
AAAI 2025 Proceedings of the 39th AAAI Conference on Artificial Intelligence
Enhancing Relation Extraction via Supervised Rationale Verification and Feedback. [Paper] [Code] [Review] [Blog (中文)]
Yongqi Li, Xin Miao, Shen Zhou, Mayi Xu, Yuyang Ren, Tieyun Qian*.
AAAI 2025 (Oral, 4.6%) Proceedings of the 39th AAAI Conference on Artificial Intelligence
A Survey on Training-free Alignment of Large Language Models. [Paper]
Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian*.
EMNLP 2025 Findings Findings of the Association for Computational Linguistics: EMNLP 2025
2024
Adaption-of-Thought: Learning Question Difficulty Improves Large Language Models for Reasoning. [Paper] [Code] [Review]
Mayi Xu, Yongqi Li, Ke Sun, Tieyun Qian*.
EMNLP 2024 Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction. [Paper] [Review]
Xin Miao, Yongqi Li, Shen Zhou, Tieyun Qian*.
ACL 2024 Findings Findings of the Association for Computational Linguistics: ACL 2024
An Ensemble-of-Experts Framework for Rehearsal-free Continual Relation Extraction. [Paper] [Code] [Review]
Shen Zhou, Yongqi Li, Xin Miao, Tieyun Qian*.
ACL 2024 Findings Findings of the Association for Computational Linguistics: ACL 2024
Prompting Large Language Models for Counterfactual Generation: An Empirical Study. [Paper] [Review] [Blog (中文)]
Yongqi Li†, Mayi Xu†, Xin Miao†, Shen Zhou†, Tieyun Qian*.
LREC-COLING 2024 Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation
2023
Generating Commonsense Counterfactuals for Stable Relation Extraction. [Paper] [Code] [Review]
Xin Miao, Yongqi Li, Tieyun Qian*.
EMNLP 2023 Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Type-Aware Decomposed Framework for Few-Shot Named Entity Recognition. [Paper] [Code] [Review] [Blog (中文)]
Yongqi Li, Yu Yu, Tieyun Qian*.
EMNLP 2023 Findings Findings of the Association for Computational Linguistics: EMNLP 2023
Service
- Conference Reviewer: ACL 2024-2025, EMNLP 2024-2025, NAACL 2024-2025, EACL 2024-2026, AAAI 2025-2026