让大模型更懂问题，用知识图谱精准生成答题提示。
Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models
- 根据问题动态筛选知识图谱相关部分，生成精准提示。
- 在多个数据集上超越现有方法，最高提升3.2个百分点。
- 适合需要外部知识的多选题问答任务，尤其对冷门选项有效。
大语言模型在需要外部知识的任务中表现不佳，如知识密集型多选题问答（MCQA）。虽然引入知识图谱（KG）可增强推理能力，但现有方法通常需要昂贵的微调或检索噪声信息。近期方法利用图神经网络（GNN）生成基于知识图谱的输入嵌入前缀作为软提示，但未考虑问题相关性，导致提示噪声。此外，在MCQA任务中，某些答案选项缺乏相关知识仍是一大挑战。为此，我们提出问题感知的知识图谱提示（QAP），将问题嵌入融入GNN聚合过程，动态评估知识图谱的相关性。QAP使用全局注意力捕捉选项间的关联关系，通过推断知识丰富软提示。实验表明，QAP在多个数据集上均优于当前最优方法，证明其有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。