FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answering

Yuan Sui, Yufei He, Nian Liu, Xiaoxin He, Kun Wang, Bryan Hooi

Track: Long Paper Track (up to 9 pages)

Keywords: Large Language Model Hallucination, Faithful Reasoning, Knowledge-enhanced LLMs, Knowledge Graphs

TL;DR: This paper presents FiDeLiS, a method combining knowledge graphs and LLMs to enhance reasoning efficiency and reduce hallucinations in downstream QA tasks.

Abstract: Large language models (LLMs) are often challenged by generating erroneous or hallucinated responses, especially in complex reasoning tasks. Leveraging knowledge graphs (KGs) as external knowledge sources has emerged as a viable solution. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this paper, we propose a unified framework, FiDeLiS, designed to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from a KG. To achieve this, we leverage step-wise beam search with a deductive scoring function, allowing the LLM to validate each reasoning step and halt the search once the question is deducible. In addition, our Path-rag module pre-selects a smaller candidate set for each beam search step, reducing computational costs by narrowing the search space. Extensive experiments show that our training-free and efficient approach outperforms strong baselines, enhancing both factuality and interpretability.

Submission Number: 148