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

2026-01-29

AI Summary

This work addresses the limitation of existing retrieval-augmented methods in scientific question answering, which often overlook deep semantic relationships among academic papers, leading to incomplete and thematically inconsistent responses. To overcome this, the authors propose a central-entity-guided approach for constructing academic knowledge subgraphs, using paper titles as anchors and integrating subgraph pruning and completion with community detection to explicitly model clusters of papers sharing common research themes. This is the first study to incorporate central-entity-guided graph optimization and community detection into a retrieval-augmented generation (RAG) framework, thereby enhancing contextual relevance and semantic coherence. Evaluated on three NLP-domain scientific QA benchmarks, the proposed method significantly outperforms current baselines, demonstrating its effectiveness in augmenting large language models for scientific question answering.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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.

Problem

• scientific question answering
• retrieval augmentation
• semantic connections
• large language models
• academic knowledge graphs

Innovation

• central entity
• graph optimization
• community detection
• retrieval-augmented LLM
• scientific question answering