Publication
(*: Equal contribution). See the full list on Google Scholar.
2026
Energy-Regularized Sequential Model Editing on Hyperspheres.
In Proceedings of the 14th International Conference on Learning Representations (ICLR 2026)
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency.
In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
ReCode: Updating Code API Knowledge with Reinforcement Learning.
In Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI 2026)
Aligning Agentic World Models via Knowledgeable Experience Learning.
Preprint
How Do Large Language Models Learn Concepts During Continual Pre-Training?
Preprint
2025
Rethinking Knowledge Editing in Reasoning Era.
Reflection on Knowledge Editing: Charting the Next Steps.
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners.
(EMNLP 2025)
Exploring Model Kinship for Merging Large Language Models.
(EMNLP 2025)
Benchmarking Chinese Knowledge Rectification in Large Language Models.
(ACL 2025)
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training.
(ACL 2025)
2024
Knowledge Circuits in Pretrained Transformers.
In Proceedings of the 38th Neural Information Processing Systems (NeurIPS 2024)
Knowledge mechanisms in large language models: A survey and perspective.
In Findings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)
A comprehensive study of knowledge editing for large language models.
2023
Unveiling the pitfalls of knowledge editing for large language models.
In Proceedings of the 12th International Conference on Learning Representations (ICLR 2023)
Editing Large Language Models: Problems, Methods, and Opportunities.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
Knowledge Rumination for Pre-trained Language Models.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
Schema-aware reference as prompt improves data-efficient knowledge graph construction.
In Proceedings of the 46th International ACM SIGIR Conference (SIGIR 2023)
2022 and Earlier
Kformer: Knowledge injection in transformer feed-forward layers.
In Proceedings of the 11th Natural Language Processing and Chinese Computing (NLPCC 2022)
Adapt-and-distill: Developing small, fast and effective pretrained language models for domains.
In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (ACL 2021)