不依赖大模型，用知识图谱+小模型重写问题来精准回答。
Interpretable Question Answering with Knowledge Graphs
- 先用小模型重写知识图谱中的关系边，提升语义理解。
- 在CRAG基准上达71.9%准确率（LLAMA-3.2）和54.4%（GPT-3.5-Turbo）。
- 适合追求可解释性与低资源推理的问答场景。
本文提出一种仅基于知识图谱检索的问答系统，不依赖大型语言模型的检索增强生成（RAG）。通过一个小规模重写模型对知识图谱查询结果中的实体关系边进行重写。整个流程分为两个阶段：第一阶段将文档预处理为问题-答案对；第二阶段将这些问答对构建为知识图谱，利用嵌入与模糊技术进行图检索、重排序和重写，最终生成答案。在CRAG基准上使用大模型作为评判者进行评估，分别取得LLAMA-3.2下71.9%和GPT-3.5-Turbo下54.4%的准确率。
原文摘要 · Abstract (English)
This paper presents a question answering system that operates exclusively on a knowledge graph retrieval without relying on retrieval augmented generation (RAG) with large language models (LLMs). Instead, a small paraphraser model is used to paraphrase the entity relationship edges retrieved from querying the knowledge graph. The proposed pipeline is divided into two main stages. The first stage involves pre-processing a document to generate sets of question-answer (QA) pairs. The second stage converts these QAs into a knowledge graph from which graph-based retrieval is performed using embeddings and fuzzy techniques. The graph is queried, re-ranked, and paraphrased to generate a final answer. This work includes an evaluation using LLM-as-a-judge on the CRAG benchmark, which resulted in accuracies of 71.9% and 54.4% using LLAMA-3.2 and GPT-3.5-Turbo, respectively.
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。