arXiv cs.CL· Yuchao Wu·· 12 小时前AI 评分38
SAG2：基于 BM25 与 JEV 的无嵌入向量多跳检索
SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
AI 导读
SAG2 是一种无嵌入向量的多跳检索架构，仅依赖单个 SQLite 数据库、BM25 和 JEV 的上下文证据决策，将语义证据选择移到查询时，省去离线嵌入计算、基于 LLM 的事件实体抽取和专用数据库服务器。
正文 · 原文
Abstract:Strong multi-hop retrieval should be practical to deploy without expensive corpus preparation or complex database infrastructure. We present SAG2, an embedding-free retrieval architecture built around a single SQLite database, BM25, and contextual evidence decisions from JEV. SAG2 follows the query-time association principle of SAG (SQL-Retrieval Augmented Generation), while replacing its event-entity and dense indexes with a lexical index over original passages. Selected passages supply terms for further retrieval, and newly retrieved evidence guides subsequent decisions. This moves semantic evidence selection to query time, eliminating offline embedding computation, LLM-based event-entity extraction, and dedicated database servers. The resulting system combines lightweight preparation with strong retrieval accuracy: on 1,000-question subsets of MuSiQue, 2WikiMultiHopQA, and HotpotQA, SAG2 achieves the highest Recall@5 and Recall@10 among the compared methods, with Recall@10 of 86.62%, 97.43%, and 99.00%. It also reaches 81.10% document Recall@10 over the 511,962-document EnterpriseRAG-Bench corpus. Indexing all 11,656 MuSiQue passages takes 2.36 seconds, produces a 25.87 MiB database, and requires no model calls. SAG2 demonstrates that accurate multi-hop evidence retrieval can be supported by compact, rapidly prepared infrastructure, making it a practical foundation for knowledge retrieval applications.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22588 [cs.CL] |
| (or arXiv:2610.22588v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22588 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuchao Wu [view email]
[v1]
Thu, 15 Oct 2026 19:37:48 UTC (184 KB)
来源：arXiv cs.CL · arxiv.org