Knowledge Graph-Infused Fine-Tuning for Structured Reasoning in Large Language Models

TL;DR

This paper introduces a knowledge graph-infused fine-tuning method for large language models that improves structured reasoning and entity understanding by integrating graph-based semantic representations with dynamic balancing mechanisms.

Contribution

It presents a novel fine-tuning framework combining knowledge graph injection, graph neural networks, and gating mechanisms to enhance reasoning and entity comprehension in language models.

Findings

Improves entity prediction accuracy.

Enhances semantic reasoning capabilities.

Demonstrates robustness across multiple NLP tasks.

Abstract

This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm framework based on knowledge graph injection. The method builds on pretrained language models and introduces structured graph information for auxiliary learning. A graph neural network is used to encode entities and their relations, constructing a graph-based semantic representation. A fusion mechanism is then designed to jointly model the knowledge graph embeddings with the contextual representations from the language model. To enhance the robustness of knowledge integration, a gating mechanism is introduced to dynamically balance the contributions of linguistic semantics and structural knowledge. This effectively mitigates conflicts between different representational spaces. During training, a joint loss function is constructed to account for both task performance and structural alignment objectives. This helps improve the accuracy of entity prediction and semantic reasoning. The study also includes a series of systematic sensitivity experiments. It evaluates the effects of learning rate, graph coverage, and structural perturbations on model performance. The results further validate the effectiveness and stability of the proposed method across tasks such as entity recognition, question answering, and language generation. Experimental findings show that the proposed structure-aware fine-tuning framework significantly enhances the model's ability to represent complex semantic units. It demonstrates better semantic consistency and contextual logic modeling in scenarios involving structural reasoning and entity extraction.