Question-Aware Knowledge Graph Prompting for Enhancing 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_ | 1866910899173851136 |
|---|---|
| author | Liu, Haochen Wang, Song Chen, Chen Li, Jundong |
| author_facet | Liu, Haochen Wang, Song Chen, Chen Li, Jundong |
| contents | Large Language Models (LLMs) often struggle with tasks requiring external knowledge, such as knowledge-intensive Multiple Choice Question Answering (MCQA). Integrating Knowledge Graphs (KGs) can enhance reasoning; however, existing methods typically demand costly fine-tuning or retrieve noisy KG information. Recent approaches leverage Graph Neural Networks (GNNs) to generate KG-based input embedding prefixes as soft prompts for LLMs but fail to account for question relevance, resulting in noisy prompts. Moreover, in MCQA tasks, the absence of relevant KG knowledge for certain answer options remains a significant challenge. To address these issues, we propose Question-Aware Knowledge Graph Prompting (QAP), which incorporates question embeddings into GNN aggregation to dynamically assess KG relevance. QAP employs global attention to capture inter-option relationships, enriching soft prompts with inferred knowledge. Experimental results demonstrate that QAP outperforms state-of-the-art methods across multiple datasets, highlighting its effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23523 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models Liu, Haochen Wang, Song Chen, Chen Li, Jundong Computation and Language Machine Learning Large Language Models (LLMs) often struggle with tasks requiring external knowledge, such as knowledge-intensive Multiple Choice Question Answering (MCQA). Integrating Knowledge Graphs (KGs) can enhance reasoning; however, existing methods typically demand costly fine-tuning or retrieve noisy KG information. Recent approaches leverage Graph Neural Networks (GNNs) to generate KG-based input embedding prefixes as soft prompts for LLMs but fail to account for question relevance, resulting in noisy prompts. Moreover, in MCQA tasks, the absence of relevant KG knowledge for certain answer options remains a significant challenge. To address these issues, we propose Question-Aware Knowledge Graph Prompting (QAP), which incorporates question embeddings into GNN aggregation to dynamically assess KG relevance. QAP employs global attention to capture inter-option relationships, enriching soft prompts with inferred knowledge. Experimental results demonstrate that QAP outperforms state-of-the-art methods across multiple datasets, highlighting its effectiveness. |
| title | Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2503.23523 |