Xiaotian Ye

According to our database1, Xiaotian Ye authored at least 11 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning.
CoRR, May, 2026

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing.
CoRR, May, 2026

Uncovering Context Reliance in Unstructured Knowledge Editing.
CoRR, February, 2026

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
LLM Unlearning Should Be Form-Independent.
CoRR, June, 2025

Disentangling Knowledge Representations for Large Language Model Editing.
CoRR, May, 2025

Open Problems and a Hypothetical Path Forward in LLM Knowledge Paradigms.
CoRR, April, 2025

Uncovering Overfitting in Large Language Model Editing.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024
Knowledge Graph Enhanced Large Language Model Editing.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024


  Loading...