Multilingual Knowledge Editing with Language-Agnostic Factual Neurons

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou


Abstract
Multilingual knowledge editing (MKE) aims to simultaneously update factual knowledge across multiple languages within large language models (LLMs). Previous research indicates that the same knowledge across different languages within LLMs exhibits a degree of shareability. However, most existing MKE methods overlook the connections of the same knowledge between different languages, resulting in knowledge conflicts and limited edit performance. To address this issue, we first investigate how LLMs process multilingual factual knowledge and discover that the same factual knowledge in different languages generally activates a shared set of neurons, which we call language-agnostic factual neurons (LAFNs). These neurons represent the same factual knowledge shared across languages and imply the semantic connections among multilingual knowledge. Inspired by this finding, we propose a new MKE method by Locating and Updating Language-Agnostic Factual Neurons (LU-LAFNs) to edit multilingual knowledge simultaneously, which avoids knowledge conflicts and thus improves edit performance. Experimental results on Bi-ZsRE and MzsRE benchmarks demonstrate that our method achieves the best edit performance, indicating the effectiveness and importance of modeling the semantic connections among multilingual knowledge.
Anthology ID:
2025.coling-main.385
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5775–5788
Language:
URL:
https://aclanthology.org/2025.coling-main.385/
DOI:
Bibkey:
Cite (ACL):
Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, and Jie Zhou. 2025. Multilingual Knowledge Editing with Language-Agnostic Factual Neurons. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5775–5788, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Multilingual Knowledge Editing with Language-Agnostic Factual Neurons (Zhang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.385.pdf