Enhancing Large Language Models with Reliable Knowledge Graphs

TL;DR

This paper proposes a comprehensive framework that improves the reliability of Knowledge Graphs and their integration with Large Language Models, leading to more accurate, interpretable, and adaptable AI systems.

Contribution

It introduces novel methods for error detection, correction, and KG completion, and demonstrates their effectiveness in enhancing LLM performance through structured reasoning.

Findings

Enhanced factual accuracy in LLMs using reliable KGs

Improved interpretability and robustness of LLMs

Effective pipeline from KG refinement to LLM integration

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in text generation and understanding, yet their reliance on implicit, unstructured knowledge often leads to factual inaccuracies and limited interpretability. Knowledge Graphs (KGs), with their structured, relational representations, offer a promising solution to ground LLMs in verified knowledge. However, their potential remains constrained by inherent noise, incompleteness, and the complexity of integrating their rigid structure with the flexible reasoning of LLMs. This thesis presents a systematic framework to address these limitations, advancing the reliability of KGs and their synergistic integration with LLMs through five interconnected contributions. This thesis addresses these challenges through a cohesive framework that enhances LLMs by refining and leveraging reliable KGs. First, we introduce contrastive error detection, a structure-based method to identify incorrect facts in KGs. This approach is extended by an attribute-aware framework that unifies structural and semantic signals for error correction. Next, we propose an inductive completion model that further refines KGs by completing the missing relationships in evolving KGs. Building on these refined KGs, KnowGPT integrates structured graph reasoning into LLMs through dynamic prompting, improving factual grounding. These contributions form a systematic pipeline (from error detection to LLM integration), demonstrating that reliable KGs significantly enhance the robustness, interpretability, and adaptability of LLMs.