用大模型自建知识图谱，提升复杂条件问答的准确率和可解释性。
KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs
- 通过多提示抽取构建文档知识图谱，结合向量检索增强推理。
- 迭代图遍历筛选相关三元组，关键实体引导二次搜索。
- 支持多模型、多数据集验证，答案带解释，适合领域问答场景。
使用大语言模型（LLMs）和检索增强生成（RAG）回答复杂条件问题仍具挑战，尤其在特定领域中通用模型表现不佳。我们提出假设：将非结构化与结构化知识（来自文档和知识图谱）引入RAG，可提升推理与答案准确性。为此，我们设计了KGCaRe，一种融合神经检索与符号推理的混合方法。KGCaRe采用多提示策略从文档中提取知识并构建知识图谱，存入图数据库；同时将文档嵌入向量库实现神经检索。通过大模型引导的迭代图遍历，系统提取相关三元组、剔除无关信息，并在初始遍历不足时利用线索实体进行二次图遍历。最终，将路径形式的知识三元组与语义检索文本一并输入定制提示，生成带解释的答案。我们在两个复杂条件问答数据集上评估，结果表明，KGCaRe在Mistral、Mixtral、GPT-3.5和GPT-4o等模型上，持续优于基线方法（如Vanilla LLM、Code Prompt、Text Prompt、Think-on-Graph、Vanilla RAG、HybridContextQA）。我们已公开该方法的软件实现管道。
原文摘要 · Abstract (English)
Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly in domain-specific contexts where general-purpose LLMs and RAG tend to underperform. We hypothesize that augmenting RAG with unstructured and structured knowledge, extracted from both documents and knowledge graphs (KGs), can improve reasoning and answer accuracy for such tasks. To test this, we propose KGCaRe, a hybrid approach that combines neural retrieval with symbolic reasoning over LLM-generated KGs. KGCaRe constructs a KG from documents using a multi-prompt extraction strategy and stores it in a graph database. Simultaneously, the documents are embedded into a vector store to enable neural retrieval. KGCaRe performs innovative iterative graph traversal guided by the LLM to extract relevant triples, prune irrelevant information, and uses additional clue entities to traverse the graph again if the initial traversal does not provide satisfactory context to generate the answer. The relevant triples extracted from the KG in path form, along with semantically retrieved text passages, are then fed into custom KGCaRe prompts to generate answers to the complex conditional questions with explanations. We evaluate KGCaRe on two complex conditional QA datasets. Our results on these datasets show that KGCaRe consistently outperforms existing baselines, including Vanilla LLM, Code Prompt, Text Prompt, Think-on-Graph, Vanilla RAG, and HybridContextQA, across multiple LLMs such as Mistral, Mixtral, GPT-3.5, and GPT-4o. We publicly release the software pipeline that we developed to implement the proposed KGCaRe approach.
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。