Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

原文：Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

作者：Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani

来源：arXiv cs.AI（人工智能）

正文

Computer Science > Artificial Intelligence

arXiv:2611.08315v1 (cs)

[Submitted on 5 Nov 2026]

Title:Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

Authors:Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani

View a PDF of the paper titled Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation, by Ali Sarabadani and 2 other authors

View PDF

Abstract:Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear. We benchmark five LLMs (GPT-5.1, Gemini 2.0 Pro, Llama 3, Qwen, and BioGPT) across five KGs: DrugBank, NeuroSynth, Cognitive Atlas, Brain Map, and GDPKG. We introduce a multitier query dataset to evaluate reasoning depth and factual accuracy under KG-aware (graph-grounded) and KG-agnostic conditions. Inter-annotator agreement was substantial, with Cohen’s kappa of 0.781 (range: 0.753-0.807) and Fleiss’ kappa of 0.77. Results show that general-purpose models, particularly GPT-5.1 and Gemini 2.0 Pro, generally outperform domain-specific models on multi-hop and high-level reasoning tasks, although performance declines as query complexity increases. KG grounding reduces hallucination rates across all evaluated models. Contrary to our initial hypothesis, domain-specific models do not consistently outperform general-purpose models on specialized tasks without graph grounding. These findings highlight the value of combining broad language-model capabilities with structured domain knowledge. We provide practical guidance for selecting LLM-KG integration strategies based on task complexity and computational constraints, and discuss hybrid neurosymbolic architectures for personalized medicine, cognitive disorder diagnosis, and explainable AI.

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)

Cite as:

arXiv:2611.08315 [cs.AI]

(or

arXiv:2611.08315v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.08315

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

人工智能 · 自然语言处理 · 机器学习

由「前沿雷达」于 2026-11-06 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。