Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA

ACL ARR 2025 May Submission6511 Authors

Abstract: Large language models (LLMs) encode vast amounts of world knowledge but remain static once trained, making timely integration of emerging facts prohibitively expensive via full retraining. Knowledge-editing techniques have thus emerged to inject or overwrite specific facts into LLMs, yet they either over-rely on superficial cues or incur complex, iterative pipelines that collapse under noisy, multi-hop conditions. We introduce $\textbf{Reason-KE}$, an end-to-end reasoning-chain-based editing framework that steers a pretrained LLM through four structured stages—fact acknowledgment, relevance determination, selective application, and final reasoning—to filter distractors in a single pass. Trained on MQuAKE-CF with up to four irrelevant facts, Reason-KE elevates Qwen2.5-7B’s multi-hop QA accuracy to 90.2\% (↑17.6 pp) while suffering merely 6.3\% drop under heavy distraction and <1\% when answers are leaked. Our quantitative analysis confirms Reason-KE’s resilience and efficiency, establishing a new state of the art for reliable LLM knowledge updates. The code will be released.

Paper Type: Short

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: chain-of-thought, fine-tuning, prompting, multihop QA, reasoning, NLP in resource-constrained settings, data-efficient training, data augmentation

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency, Data resources

Languages Studied: English

Submission Number: 6511