Knowledge Homophily in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915731980943360 |
|---|---|
| author | Sahu, Utkarsh Qi, Zhisheng Halappanavar, Mahantesh Lipka, Nedim Rossi, Ryan A. Dernoncourt, Franck Zhang, Yu Ma, Yao Wang, Yu |
| author_facet | Sahu, Utkarsh Qi, Zhisheng Halappanavar, Mahantesh Lipka, Nedim Rossi, Ryan A. Dernoncourt, Franck Zhang, Yu Ma, Yao Wang, Yu |
| contents | Large Language Models (LLMs) have been increasingly studied as neural knowledge bases for supporting knowledge-intensive applications such as question answering and fact checking. However, the structural organization of their knowledge remains unexplored. Inspired by cognitive neuroscience findings, such as semantic clustering and priming, where knowing one fact increases the likelihood of recalling related facts, we investigate an analogous knowledge homophily pattern in LLMs. To this end, we map LLM knowledge into a graph representation through knowledge checking at both the triplet and entity levels. After that, we analyze the knowledgeability relationship between an entity and its neighbors, discovering that LLMs tend to possess a similar level of knowledge about entities positioned closer in the graph. Motivated by this homophily principle, we propose a Graph Neural Network (GNN) regression model to estimate entity-level knowledgeability scores for triplets by leveraging their neighborhood scores. The predicted knowledgeability enables us to prioritize checking less well-known triplets, thereby maximizing knowledge coverage under the same labeling budget. This not only improves the efficiency of active labeling for fine-tuning to inject knowledge into LLMs but also enhances multi-hop path retrieval in reasoning-intensive question answering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23773 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Knowledge Homophily in Large Language Models Sahu, Utkarsh Qi, Zhisheng Halappanavar, Mahantesh Lipka, Nedim Rossi, Ryan A. Dernoncourt, Franck Zhang, Yu Ma, Yao Wang, Yu Machine Learning Artificial Intelligence Computation and Language Social and Information Networks Large Language Models (LLMs) have been increasingly studied as neural knowledge bases for supporting knowledge-intensive applications such as question answering and fact checking. However, the structural organization of their knowledge remains unexplored. Inspired by cognitive neuroscience findings, such as semantic clustering and priming, where knowing one fact increases the likelihood of recalling related facts, we investigate an analogous knowledge homophily pattern in LLMs. To this end, we map LLM knowledge into a graph representation through knowledge checking at both the triplet and entity levels. After that, we analyze the knowledgeability relationship between an entity and its neighbors, discovering that LLMs tend to possess a similar level of knowledge about entities positioned closer in the graph. Motivated by this homophily principle, we propose a Graph Neural Network (GNN) regression model to estimate entity-level knowledgeability scores for triplets by leveraging their neighborhood scores. The predicted knowledgeability enables us to prioritize checking less well-known triplets, thereby maximizing knowledge coverage under the same labeling budget. This not only improves the efficiency of active labeling for fine-tuning to inject knowledge into LLMs but also enhances multi-hop path retrieval in reasoning-intensive question answering. |
| title | Knowledge Homophily in Large Language Models |
| topic | Machine Learning Artificial Intelligence Computation and Language Social and Information Networks |
| url | https://arxiv.org/abs/2509.23773 |