The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914029386072064 |
|---|---|
| author | Cheng, Yi-Jie Chew, Oscar Chen, Yun-Nung |
| author_facet | Cheng, Yi-Jie Chew, Oscar Chen, Yun-Nung |
| contents | Integrating knowledge graphs (KGs) into the reasoning processes of large language models (LLMs) has emerged as a promising approach to mitigate hallucination. However, existing work in this area often relies on proprietary or extremely large models, limiting accessibility and scalability. In this study, we investigate the capabilities of existing integration methods for small language models (SLMs) in KG-based question answering and observe that their performance is often constrained by their limited ability to traverse and reason over knowledge graphs. To address this limitation, we propose leveraging simple and efficient exploration modules to handle knowledge graph traversal in place of the language model itself. Experiment results demonstrate that these lightweight modules effectively improve the performance of small language models on knowledge graph question answering tasks. Source code: https://github.com/yijie-cheng/SLM-ToG/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07399 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering Cheng, Yi-Jie Chew, Oscar Chen, Yun-Nung Computation and Language Integrating knowledge graphs (KGs) into the reasoning processes of large language models (LLMs) has emerged as a promising approach to mitigate hallucination. However, existing work in this area often relies on proprietary or extremely large models, limiting accessibility and scalability. In this study, we investigate the capabilities of existing integration methods for small language models (SLMs) in KG-based question answering and observe that their performance is often constrained by their limited ability to traverse and reason over knowledge graphs. To address this limitation, we propose leveraging simple and efficient exploration modules to handle knowledge graph traversal in place of the language model itself. Experiment results demonstrate that these lightweight modules effectively improve the performance of small language models on knowledge graph question answering tasks. Source code: https://github.com/yijie-cheng/SLM-ToG/. |
| title | The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.07399 |