CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question Answering

TL;DR

CE-GOCD enhances scientific question answering by explicitly modeling semantic structures in academic knowledge graphs, improving LLM comprehension and response quality through community detection and subgraph optimization.

Contribution

This paper introduces CE-GOCD, a novel method that leverages central entities and community detection to improve knowledge graph-based retrieval for LLM scientific question answering.

Findings

Outperforms baseline retrieval methods on NLP literature QA datasets.

Effectively models semantic substructures within academic knowledge graphs.

Improves LLM response specificity and comprehensiveness.

Abstract

Large Language Models (LLMs) are increasingly used for question answering over scientific research papers. Existing retrieval augmentation methods often rely on isolated text chunks or concepts, but overlook deeper semantic connections between papers. This impairs the LLM's comprehension of scientific literature, hindering the comprehensiveness and specificity of its responses. To address this, we propose Central Entity-Guided Graph Optimization for Community Detection (CE-GOCD), a method that augments LLMs' scientific question answering by explicitly modeling and leveraging semantic substructures within academic knowledge graphs. Our approach operates by: (1) leveraging paper titles as central entities for targeted subgraph retrieval, (2) enhancing implicit semantic discovery via subgraph pruning and completion, and (3) applying community detection to distill coherent paper groups with shared themes. We evaluated the proposed method on three NLP literature-based question-answering datasets, and the results demonstrate its superiority over other retrieval-augmented baseline approaches, confirming the effectiveness of our framework.