LCR-RAG: Enhancing Logical Consistency in Retrieval-Augmented Generation via Neuro-symbolic Reinforcement Learning

ACL ARR 2026 January Submission3355 Authors

Keywords: Retrieval-Augmented Generation, Logical Reasoning, Neuro-Symbolic Methods, Reinforcement Learning, Large Language Models

Abstract:

Retrieval-Augmented Generation (RAG) is widely used to ground large language models (LLMs) in external knowledge and improve factual accuracy. Prior work has explored iterative and self-reflective mechanisms to refine reasoning, but these approaches rely on internal model judgment and lack formally grounded, verifiable feedback. As a result, RAG systems may still produce logically inconsistent or contradictory answers in multi-step reasoning.
In this paper, we propose LCR-RAG, a framework that integrates neuro-symbolic verification with reinforcement learning to explicitly optimize logical consistency. The core of our approach is a Logic-Consistency-driven Reward (LCR), which converts discrete logical signals—such as contradictions or incomplete inference chains—into a structured reward signal. This reward guides a PPO-based agent to iteratively rewrite queries and correct reasoning errors.
Experiments on HotpotQA, ASQA, and TriviaQA show that LCR-RAG consistently outperforms strong RAG baselines, with ablation results indicating that the LCR mechanism is the primary source of improvement, even under noisy or conflicting retrieval conditions.

Paper Type: Long

Research Area: Retrieval-Augmented Language Models

Research Area Keywords: retrieval-augmented generation, reinforcement learning, logical reasoning, neurosymbolic approaches

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Theory

Languages Studied: English

Submission Number: 3355