EUVIMEDEUVIMED entdecken
Crossref

FiNE: Fine-Grained Neuron-Level Model Editing for Reliable and Safe LLMs

Xun Yang, Haowen Pan, Xiaozhi Wang, Yixin Cao, Juanzi Li, Meng Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-10 · 48 (10) · 12181-12195

DOI: 10.1109/tpami.2026.3697976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-10. Verfasst von Xun Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Yangtze River Delta Science and Technology Innovation Community Joint Research, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of Large Language Models (LLMs) has underscored the need for editing techniques that enhance both the reliability and safety of model outputs. While prior locate-then-edit methods, such as ROME, achieve factual correction via causal tracing, they often overlook the internal structure of Feed-Forward Networks (FFNs) and the relational context among edited concepts, leading to brittle or incomplete updates. To address these limitations, we propose FiNE (Fine-grained Neuron-level Editing), a unified locate-then-edit framework that performs gradient-free localization and fine-grained parameter adjustment within FFNs. FiNE introduces a theoretically grounded contribution score, which can be interpreted as an efficient variant of gradient-based methods, to identify concept-relevant neurons. It further employs a composite loss to balance editing accuracy, model consistency, and output diversity. We instantiate FiNE for two complementary applications, knowledge editing (FiNE-K) and safety editing (FiNE-S), which together demonstrate the versatility of the framework. Extensive experiments on the KnowEdit and SafeEdit benchmarks show that FiNE achieves superior precision, robustness, and efficiency with minimal disruption to the model's general behavior. These results highlight the effectiveness and scalability of fine-grained neuron editing as a unified approach to building more reliable and safer LLMs.

Förderung

  • National Natural Science Foundation of China
  • Yangtze River Delta Science and Technology Innovation Community Joint Research
  • Beijing Natural Science Foundation
  • NSFC

Zitieren

APA

Yang, X., Pan, H., Wang, X., Cao, Y., Li, J., & Wang, M. (2026). FiNE: Fine-Grained Neuron-Level Model Editing for Reliable and Safe LLMs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(10), 12181-12195. https://doi.org/10.1109/tpami.2026.3697976

Vancouver

Yang X, Pan H, Wang X, Cao Y, Li J, Wang M. FiNE: Fine-Grained Neuron-Level Model Editing for Reliable and Safe LLMs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(10):12181-12195. doi:10.1109/tpami.2026.3697976

BibTeX
@article{Yang2026,
  author = {Yang, Xun and Pan, Haowen and Wang, Xiaozhi and Cao, Yixin and Li, Juanzi and Wang, Meng},
  title = {FiNE: Fine-Grained Neuron-Level Model Editing for Reliable and Safe LLMs},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {10},
  pages = {12181--12195},
  doi = {10.1109/tpami.2026.3697976}
}
Kostenlos starten →