EUVIMEDEUVIMED entdecken
Crossref

Editing Is a Bargaining Game: Balanced Knowledge Editing in Large Language Models

Chenghao Xu, Jiexi Yan, Muli Yang, Fen Fang, Huilin Chen, Cheng Deng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 34097-34105

DOI: 10.1609/aaai.v40i40.40704 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chenghao Xu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) are prone to generating incorrect or outdated information, thereby necessitating efficient and precise mechanisms for knowledge updates. Existing knowledge editing approaches, however, often encounter conflicts between two competing objectives: maintaining existing knowledge (preservation) and incorporating new information (editing). During gradient-based optimization, these conflicting objectives can lead to imbalanced update directions, where one gradient dominates, ultimately resulting in suboptimal learning dynamics. To address this challenge, we propose a balanced knowledge editing framework inspired by Nash bargaining theory. Our method guides the optimization process toward a Pareto stationary point, ensuring an equilibrium solution wherein any deviation from the final state would degrade the overall performance with respect to both objectives. This guarantees optimality in preserving prior knowledge while integrating new information. We empirically validate the effectiveness of our approach across a range of evaluation metrics on standard benchmark datasets. Extensive experiments show that our method consistently outperforms state-of-the-art techniques, achieving a superior balance between knowledge preservation and update accuracy.

Zitieren

APA

Xu, C., Yan, J., Yang, M., Fang, F., Chen, H., & Deng, C. (2026). Editing Is a Bargaining Game: Balanced Knowledge Editing in Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34097-34105. https://doi.org/10.1609/aaai.v40i40.40704

Vancouver

Xu C, Yan J, Yang M, Fang F, Chen H, Deng C. Editing Is a Bargaining Game: Balanced Knowledge Editing in Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):34097-34105. doi:10.1609/aaai.v40i40.40704

BibTeX
@article{Xu2026,
  author = {Xu, Chenghao and Yan, Jiexi and Yang, Muli and Fang, Fen and Chen, Huilin and Deng, Cheng},
  title = {Editing Is a Bargaining Game: Balanced Knowledge Editing in Large Language Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {40},
  pages = {34097--34105},
  doi = {10.1609/aaai.v40i40.40704}
}
Kostenlos starten →