Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning

TL;DR

Micro-Act introduces a hierarchical, action-based framework that improves retrieval-augmented generation by effectively resolving knowledge conflicts, leading to higher question-answering accuracy across diverse datasets.

Contribution

It proposes a novel hierarchical action space for adaptive knowledge comparison, enhancing LLM reasoning and conflict mitigation in RAG systems.

Findings

Significant accuracy improvements over baselines on five datasets.

Effective handling of temporal and semantic conflicts.

Robust performance on non-conflict questions.

Abstract

Retrieval-Augmented Generation (RAG) systems commonly suffer from Knowledge Conflicts, where retrieved external knowledge contradicts the inherent, parametric knowledge of large language models (LLMs). It adversely affects performance on downstream tasks such as question answering (QA). Existing approaches often attempt to mitigate conflicts by directly comparing two knowledge sources in a side-by-side manner, but this can overwhelm LLMs with extraneous or lengthy contexts, ultimately hindering their ability to identify and mitigate inconsistencies. To address this issue, we propose Micro-Act a framework with a hierarchical action space that automatically perceives context complexity and adaptively decomposes each knowledge source into a sequence of fine-grained comparisons. These comparisons are represented as actionable steps, enabling reasoning beyond the superficial context. Through extensive experiments on five benchmark datasets, Micro-Act consistently achieves significant increase in QA accuracy over state-of-the-art baselines across all 5 datasets and 3 conflict types, especially in temporal and semantic types where all baselines fail significantly. More importantly, Micro-Act exhibits robust performance on non-conflict questions simultaneously, highlighting its practical value in real-world RAG applications.