GNN-RAG：用于大型语言模型推理的图神经检索
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
AI总结：
本文提出GNN-RAG框架，通过GNN在知识图谱子图上推理检索答案候选并提取路径，结合LLM的检索增强生成能力进行问答，在WebQSP和CWQ基准上以7B微调模型匹配GPT-4性能，并在多跳多实体问题上显著领先。
摘要：
知识图谱（KGs）以三元组（头实体，关系，尾实体）的形式表示人类创建的事实知识，这些三元组共同构成了一个图。基于知识图谱的问答（KGQA）是将推理建立在KG提供的信息基础上来回答自然问题的任务。大型语言模型（LLMs）由于其卓越的自然语言理解能力，成为了问答任务的最新模型。另一方面，图神经网络（GNNs）已被广泛用于KGQA，因为它们能够处理存储在KG中的复杂图信息。在这项工作中，我们引入了GNN-RAG，这是一种以检索增强生成（RAG）风格将LLMs的语言理解能力与GNNs的推理能力相结合的新方法。首先，GNN在密集的KG子图上进行推理，以检索给定问题的答案候选。其次，提取KG中连接问题实体和答案候选的最短路径，以表示KG推理路径。提取的路径被语言化并作为带有RAG的LLM推理的输入。在我们的GNN-RAG框架中，GNN充当密集子图推理器以提取有用的图信息，而LLM则利用其自然语言处理能力进行最终的KGQA。此外，我们开发了一种检索增强（RA）技术，以进一步提升GNN-RAG的KGQA性能。实验结果表明，GNN-RAG在两个广泛使用的KGQA基准（WebQSP和CWQ）上取得了最先进的性能，使用7B微调LLM超越或匹配了GPT-4的性能。此外，GNN-RAG在多跳和多实体问题上表现出色，在答案F1上比竞争方法高出8.9--15.5个百分点。
英文摘要：
Knowledge Graphs (KGs) represent human-crafted factual knowledge in the form of triplets (head, relation, tail), which collectively form a graph. Question Answering over KGs (KGQA) is the task of answering natural questions grounding the reasoning to the information provided by the KG. Large Language Models (LLMs) are the state-of-the-art models for QA tasks due to their remarkable ability to understand natural language. On the other hand, Graph Neural Networks (GNNs) have been widely used for KGQA as they can handle the complex graph information stored in the KG. In this work, we introduce GNN-RAG, a novel method for combining language understanding abilities of LLMs with the reasoning abilities of GNNs in a retrieval-augmented generation (RAG) style. First, a GNN reasons over a dense KG subgraph to retrieve answer candidates for a given question. Second, the shortest paths in the KG that connect question entities and answer candidates are extracted to represent KG reasoning paths. The extracted paths are verbalized and given as input for LLM reasoning with RAG. In our GNN-RAG framework, the GNN acts as a dense subgraph reasoner to extract useful graph information, while the LLM leverages its natural language processing ability for ultimate KGQA. Furthermore, we develop a retrieval augmentation (RA) technique to further boost KGQA performance with GNN-RAG. Experimental results show that GNN-RAG achieves state-of-the-art performance in two widely used KGQA benchmarks (WebQSP and CWQ), outperforming or matching GPT-4 performance with a 7B tuned LLM. In addition, GNN-RAG excels on multi-hop and multi-entity questions outperforming competing approaches by 8.9--15.5% points at answer F1.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
