<ul><li>Large Language Models (LLMs) struggle with tasks requiring external knowledge.</li><li>Knowledge Graphs (KGs) can enhance reasoning, but existing methods demand costly fine-tuning or retrieve noisy KG information.</li><li>Question-Aware Knowledge Graph Prompting (QAP) dynamically assesses KG relevance and incorporates question embeddings into reasoning.</li><li>Experimental results demonstrate that QAP outperforms state-of-the-art methods in Multiple Choice Question Answering tasks.</li></ul>

Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models

Discover more