Grounding LLM Reasoning with Knowledge Graphs

Alfonso Amayuelas, Joy Prakash Sain, Simerjot Kaur, Charese Smiley

Keywords: Large Language Models, Knowledge Graphs, Reasoning, Graph Reasoning, Question-Answering, Grounded Reasoning, Structured Kowledge

TL;DR: We ground LLM reasoning in knowledge graphs, linking each step to structured data, improving accuracy and interpretability with up to 26.5% gains over CoT baselines on GRBench.

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.

Submission Number: 131