DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models

Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang


Abstract
Recently, while large language models (LLMs) have demonstrated impressive results, they still suffer from hallucination, i.e., the generation of false information. Model editing is the task of fixing factual mistakes in LLMs; yet, most previous works treat it as a one-time task, paying little attention to ever-emerging mistakes generated by LLMs. We address the task of sequential model editing (SME) that aims to rectify mistakes continuously. A Dynamic Auxiliary Fusion Network (DAFNet) is designed to enhance the semantic interaction among the factual knowledge within the entire sequence, preventing catastrophic forgetting during the editing process of multiple knowledge triples.Specifically, (1) for semantic fusion within a relation triple, we aggregate the intra-editing attention flow into auto-regressive self-attention with token-level granularity in LLMs. We further leverage multi-layer diagonal inter-editing attention flow to update the weighted representations of the entire sequence-level granularity. (2) Considering that auxiliary parameters are required to store the knowledge for sequential editing, we construct a new dataset named DAFSet, fulfilling recent, popular, long-tail and robust properties to enhance the generality of sequential editing. Experiments show DAFNet significantly outperforms strong baselines in single-turn and sequential editing. The usage of DAFSet also consistently improves the performance of other auxiliary network-based methods in various scenarios.
Anthology ID:
2024.findings-acl.92
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1588–1602
Language:
URL:
https://aclanthology.org/2024.findings-acl.92
DOI:
10.18653/v1/2024.findings-acl.92
Bibkey:
Cite (ACL):
Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, and Jun Huang. 2024. DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 1588–1602, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models (Zhang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.92.pdf