用知识图谱增强大模型多跳推理，减少幻觉。
Multi-hop Reasoning and Retrieval in Embedding Space: Leveraging Large Language Models with Knowledge
- 基于知识图谱生成逻辑规则，在嵌入空间中推理
- 在两个基准数据集上达到新最优性能
- 适合需要可靠推理的问答与知识增强任务
随着大语言模型（LLMs）规模持续增长，其解决复杂任务的能力显著提升。然而，幻觉和缺乏最新知识等问题仍未能解决。知识图谱（KG）作为现实世界知识的符号化表示，可提供可靠知识以增强推理能力。将知识图谱检索融入大模型，有助于提升其推理可靠性。然而，由于对底层知识图谱理解有限，大模型可能难以处理具有多重解释的查询；同时，知识图谱的不完整性和噪声可能导致检索失败。为此，我们提出一种基于嵌入空间的检索推理框架 EMBRAG。该方法首先根据输入查询生成多个基于知识图谱的逻辑规则，随后在嵌入空间中结合知识图谱进行推理，确保更鲁棒、准确的推理过程。一个重排序模型进一步解析这些规则并优化结果。在两个基准知识图谱问答（KGQA）数据集上的大量实验表明，该方法在知识图谱推理任务中达到新的最先进水平。
原文摘要 · Abstract (English)
As large language models (LLMs) continue to grow in size, their abilities to tackle complex tasks have significantly improved. However, issues such as hallucination and the lack of up-to-date knowledge largely remain unresolved. Knowledge graphs (KGs), which serve as symbolic representations of real-world knowledge, offer a reliable source for enhancing reasoning. Integrating KG retrieval into LLMs can therefore strengthen their reasoning by providing dependable knowledge. Nevertheless, due to limited understanding of the underlying knowledge graph, LLMs may struggle with queries that have multiple interpretations. Additionally, the incompleteness and noise within knowledge graphs may result in retrieval failures. To address these challenges, we propose an embedding-based retrieval reasoning framework EMBRAG. In this approach, the model first generates multiple logical rules grounded in knowledge graphs based on the input query. These rules are then applied to reasoning in the embedding space, guided by the knowledge graph, ensuring more robust and accurate reasoning. A reranker model further interprets these rules and refines the results. Extensive experiments on two benchmark KGQA datasets demonstrate that our approach achieves the new state-of-the-art performance in KG reasoning tasks.
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。