让大模型问答过程可解释，自动识别缺失信息并追问。
NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
- 用逻辑语言生成可追溯的推理步骤，每步都有来源
- 在ShARC上准确率达61.1%，比基线高18.3个百分点
- 适合需要透明推理和交互式澄清的复杂问答场景
检索增强生成（RAG）通过引入外部文本知识提升大模型问答能力，但其推理过程缺乏透明性：中间步骤难以验证，且无法可靠关联具体证据。此外，用户特定上下文缺失常被忽略，导致回答不完整或错误。本文提出NeSy-RAG，一种模块化神经符号检索增强生成框架，从检索到的文本片段中合成可追溯的Prolog模块。每个片段生成语义明确的谓词，编码布尔命题，可能依赖用户事实。通过联合自然语言与代码嵌入，谓词被检索并组合成Prolog查询。为解决用户上下文不完整问题，引入符号知识缺口检测机制，识别影响查询结果的关键缺失事实，并自动触发后续交互。执行生成的Prolog查询可获得确定性答案及透明的执行轨迹，每一步均关联原始来源。在ShARC基准测试中，无需领域训练，NeSy-RAG达到61.1%准确率，优于同模型基线的42.8%。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often leading to incomplete or incorrect output. We propose NeSy-RAG, a modular neuro-symbolic RAG framework that synthesizes attributable Prolog modules from retrieved text chunks. For each chunk, the system generates semantically meaningful predicates that encode Boolean claims, which may depend on user facts. Using joint natural language-code embeddings, predicates are retrieved and composed into Prolog queries. To address incomplete user context, we introduce a symbolic knowledge-gap detection mechanism that identifies missing user facts whose truth values affect the query outcome and automatically triggers follow-up interactions. Executing the resulting Prolog queries yields deterministic answers together with transparent execution traces that link each reasoning step to its originating source. On the ShARC benchmark, without domain-specific training, NeSy-RAG achieves 61.1% accuracy, outperforming a same-model RAG baseline that achieves 42.8% accuracy.
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。