Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Tianyi, He, Yinhan, Zheng, Wendy, Chen, Chen
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.05876
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911573703917568
author Zhao, Tianyi
He, Yinhan
Zheng, Wendy
Chen, Chen
author_facet Zhao, Tianyi
He, Yinhan
Zheng, Wendy
Chen, Chen
contents Deploying Large Language Models (LLMs) in real-world dynamic environments raises the challenge of updating their pre-trained knowledge. While existing knowledge editing methods can reliably patch isolated facts, they frequently suffer from a "Reasoning Gap", where the model recalls the edited fact but fails to utilize it in multi-step reasoning chains. To bridge this gap, we introduce MCircKE (\underline{M}echanistic \underline{Circ}uit-based \underline{K}nowledge \underline{E}diting), a novel framework that enables a precise "map-and-adapt" editing procedure. MCircKE first identifies the causal circuits responsible for a specific reasoning task, capturing both the storage of the fact and the routing of its logical consequences. It then surgically update parameters exclusively within this mapped circuit. Extensive experiments on the MQuAKE-3K benchmark demonstrate the effectiveness of the proposed method for multi-hop reasoning in knowledge editing.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05876
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Mechanistic Circuit-Based Knowledge Editing in Large Language Models
Zhao, Tianyi
He, Yinhan
Zheng, Wendy
Chen, Chen
Computation and Language
Deploying Large Language Models (LLMs) in real-world dynamic environments raises the challenge of updating their pre-trained knowledge. While existing knowledge editing methods can reliably patch isolated facts, they frequently suffer from a "Reasoning Gap", where the model recalls the edited fact but fails to utilize it in multi-step reasoning chains. To bridge this gap, we introduce MCircKE (\underline{M}echanistic \underline{Circ}uit-based \underline{K}nowledge \underline{E}diting), a novel framework that enables a precise "map-and-adapt" editing procedure. MCircKE first identifies the causal circuits responsible for a specific reasoning task, capturing both the storage of the fact and the routing of its logical consequences. It then surgically update parameters exclusively within this mapped circuit. Extensive experiments on the MQuAKE-3K benchmark demonstrate the effectiveness of the proposed method for multi-hop reasoning in knowledge editing.
title Mechanistic Circuit-Based Knowledge Editing in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2604.05876