Grounding LLM Reasoning with Knowledge Graphs

TL;DR

This paper introduces a framework that enhances LLM reasoning by grounding it in Knowledge Graphs, improving accuracy, interpretability, and consistency in complex reasoning tasks through multiple strategies and benchmark evaluation.

Contribution

It presents a novel integration of LLM reasoning with Knowledge Graphs using multiple reasoning strategies, achieving state-of-the-art performance and providing insights into reasoning dynamics.

Findings

Achieved at least 26.5% improvement over CoT baselines.

Grounding improves interpretability and consistency of reasoning.

Analyzed factors influencing reasoning quality, such as step depth and model size.

Abstract

Large Language Models (LLMs) excel at generating natural language answers, yet their outputs often remain unverifiable and difficult to trace. Knowledge Graphs (KGs) offer a complementary strength by representing entities and their relationships in structured form, providing a foundation for more reliable reasoning. We propose a novel framework that integrates LLM reasoning with KGs by linking each step of the reasoning process to graph-structured data. This grounding turns intermediate ``thoughts'' into interpretable traces that remain consistent with external knowledge. Our approach incorporates multiple reasoning strategies, Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT), and is evaluated on GRBench, a benchmark for domain-specific graph reasoning. Our experiments show state-of-the-art (SOTA) performance, with at least 26.5\% improvement over CoT baselines. Beyond accuracy, we analyze how step depth, branching structure, and model size influence reasoning quality, offering insights into the conditions that support effective reasoning. Together, these contributions highlight how grounding LLMs in structured knowledge enables both higher accuracy and greater interpretability in complex reasoning tasks.