Addressing the Reasoning Gap: Mechanistic Circuit-Based Knowledge Editing in Large Language Models

ACL ARR 2026 January Submission7500 Authors

Keywords: Knowledge Editing, Large Language Models, Mechanistic Interpretability

Abstract:

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.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: model editing, knowledge tracing/discovering/inducing

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 7500