arXiv cs.CL· Valentin Six, Mufei Li, Dongqi Fu, Yinglong Xia, Hong Li, Pan Li·· 11 小时前AI 评分34
RAGCompass：通过重排序实现可泛化的检索器路由
RAGCompass: Generalizable Retriever Routing via Reranking
AI 导读
RAGCompass 通过读取检索到的段落集合本身来做检索器路由，而非依赖查询特征，从而能处理未见过的检索器和语料。其对比式微调的重排序器贡献了主要增益，小型比较头带来适度提升，且两个组件均无检索器专属参数。相比最佳固定检索器，答案 F1 相对提升 28%，并优于融合基线、三个仅查询路由器及一个提示的 8B 语言模型；在未见语料、检索器或阅读器下仍保留大部分增益。
正文 · 原文
Abstract:Different retrievers exist for retrieval-augmented generation, yet none performs best for all queries. Therefore, the key question is: given a query and retrieved passages from different retrievers, which one is most suited for that query? Existing routers usually make predictions from query-specific features and a fixed pool of retrievers; such routers have no output for an unseen retriever and are incapable by design on a new corpus. To fill these gaps, RAGCompass reads the retrieved passage sets themselves: passages from an unfamiliar retriever or corpus stay directly comparable to other passages, so routing stays well designed where a query-only map would fail. We contrastively fine-tune a reranker against the answer each evidence set produces, which accounts for most of the gain; a small comparison head adds a moderate improvement, and neither component has retriever-specific parameters. RAGCompass improves answer F1 by 28% relative to the best fixed retriever, and outperforms fusion baselines, three query-only routers, and a prompted 8B language model. Generalization experiments show that RAGCompass keeps most of its gain under an unseen corpus, retriever, or reader, while query-only baselines fall to the best fixed retriever or below.
| Subjects: | Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2611.05596 [cs.CL] |
| (or arXiv:2611.05596v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05596 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Valentin Six [view email]
[v1]
Tue, 3 Nov 2026 20:36:24 UTC (420 KB)
来源：arXiv cs.CL · arxiv.org