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

arXiv:2604.05876v2 Announce Type: replace 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 extit{reasoning gap}, where the model recalls the edited fact but fails to utilize it in multi-step reasoning chains. Our analysis shows that multi-hop reasoning relies on sparse circuitry beyond direct factual recall, with functionally differentiated components contributing to intermediate processing and final-answer prediction. To bridge this gap, we introduce MCircKE (nderline{M}echanistic nderline{Circ}uit-based nderline{K}nowledge nderline{E}diting), a mechanistically grounded framework that enables a 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-series benchmarks demonstrate the effectiveness of the proposed method for multi-hop reasoning in knowledge editing.

Related

• Energy-Regularized Sequential Model Editing on Hyperspheres
• Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
• CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance

Source: arXiv cs.CL | 2026-08-27