Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing

2025-05-31

AI Summary

Existing in-context editing (ICE) methods struggle to disentangle newly injected knowledge from the model’s intrinsic parametric knowledge, leading to knowledge conflicts and inconsistent multi-hop reasoning. To address this, we propose a lightweight, parameter-free decoupled ICE framework that explicitly isolates knowledge injection from native inference via reasoning-path masking. Our approach integrates prompt engineering, dynamic path-mask generation, external knowledge retrieval, and in-model self-verification into an end-to-end interpretable editing pipeline. Crucially, it employs a hybrid retrieval–LLM self-verification mechanism to jointly ensure factual accuracy and reasoning-path consistency. Evaluated on multi-hop question answering benchmarks, our method significantly outperforms state-of-the-art ICE approaches, achieving simultaneous improvements in editing accuracy and reasoning consistency. The implementation is publicly available.

Technology Category

• Knowledge Representation and Reasoning: Reasoning with Beliefs
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by injecting new knowledge directly into the input context, leaving model parameters unchanged. However, existing ICE approaches do not explicitly separate the newly injected knowledge from the model's original reasoning process. This entanglement often results in conflicts between external updates and internal parametric knowledge, undermining the consistency and accuracy of the reasoning path.In this work, we conduct preliminary experiments to examine how parametric knowledge influences reasoning path planning. We find that the model's reasoning is tightly coupled with its internal knowledge, and that naively injecting new information without adapting the reasoning path often leads to performance degradation, particularly in multi-hop tasks. To this end, we propose DecKER, a novel ICE framework that decouples reasoning from knowledge editing by generating a masked reasoning path and then resolving knowledge edits via hybrid retrieval and model-based validation. Experiments on multi-hop QA benchmarks show that DecKER significantly outperforms existing ICE methods by mitigating knowledge conflicts and preserving reasoning consistency. Our code is available at: https://github.com/bebr2/DecKER .

Problem

• Decoupling reasoning from knowledge injection in LLMs
• Mitigating conflicts between external updates and internal knowledge
• Improving consistency and accuracy in multi-hop reasoning tasks

Innovation

• Decouples reasoning and knowledge editing processes
• Uses masked reasoning path for clarity
• Employs hybrid retrieval and validation