arXiv cs.AI· Wadie El Amrani, Luis Gal\'arraga·· 13 小时前AI 评分31
GraphRAGProv：让 GraphRAG 具备 How-Provenance 溯源能力
GraphRAGProv: GraphRAG Meets How-Provenance
AI 导读
GraphRAGProv 通过在源文本锚定的 RDF 图上执行 SPARQL 查询，计算答案及其 how-provenance 多项式，记录使用了哪些语句出现以及如何组合，用户可沿链接核查抽取语句是否忠实原文。其交互式演示检查了两个多跳 QA 基准的 400 个案例，发现即使最终答案正确，也存在抽取和查询错误。
正文 · 原文
Abstract:GraphRAG systems often use knowledge graphs to retrieve relevant context for an LLM that produces the final answer. That makes answers more inscrutable and therefore less appealing for domains where transparency is paramount. We present GraphRAGProv, an architecture that executes SPARQL queries over source-grounded RDF graphs to compute answers and their how-provenance polynomials. These polynomials record which statement occurrences were used and how they were combined. Because each occurrence is linked to its source text, users can follow these links to check whether the extracted statements reflect the text and whether the query combines them to answer the question. Querying thereby becomes a way to inspect and evaluate the text-to-graph transformation. Our interactive demo examines 400 cases from two multi-hop QA benchmarks, revealing extraction and query errors even when the final answer is correct.
| Subjects: | Artificial Intelligence (cs.AI); Databases (cs.DB) |
| ACM classes: | I.2; H.2 |
| Cite as: | arXiv:2610.37237 [cs.AI] |
| (or arXiv:2610.37237v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37237 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Luis Galárraga [view email]
[v1]
Tue, 27 Oct 2026 13:42:48 UTC (10,869 KB)
来源：arXiv cs.AI · arxiv.org