← 研踪 PaperTrailarXiv:2611.16366 · v1
CURATOR: Scalable Fine-grained Evidence Selection for Retrieval-Augmented Generation using Decision Models
首次提交 2026-11-12 14:29
版本更新 2026-11-12 14:29
雷达观测 2026-11-13 14:15
摘要
Retrieval-augmented generation (RAG) provides entire retrieved passages to the LLM, even though only a handful of spans within them contain the evidence pertaining to the question. While precise selection of these spans can improve context utilization, identifying them in isolation is challenging. A span may appear irrelevant by itself, and deciding whether to retain it may require examining other retrieved information. One can evaluate each span's candidacy with the full retrieved context, but this is computationally inefficient as the same text must be processed repeatedly. Pretrained decision model can be used to efficiently evaluate multiple spans simultaneously, allowing each decision to consider the surrounding spans as well. However, our experiments show that their ability to identify relevant evidence deteriorates as the number of simultaneous decisions increases. To address this, we introduce CURATOR, a fine-tuned decision model trained to make reliable evidence-selection decisions over large candidate sets. By training a decision model to select varying numbers of supporting spans from large candidate pools, CURATOR develops the capability to select evidence for RAG while retaining the computational efficiency of joint decision-making. We observe that CURATOR maintains a strong evidence discrimination capability as the number of candidates increases, generalizes across different tasks and document domains, and improves downstream RAG performance, particularly when the available context is limited.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-12 14:29 · 最新观测版本
CURATOR: Scalable Fine-grained Evidence Selection for Retrieval-Augmented Generation using Decision Models
Retrieval-augmented generation (RAG) provides entire retrieved passages to the LLM, even though only a handful of spans within them contain the evidence pertaining to the question. While precise selection of these spans can improve context utilization, identifying them in isolation is challenging. A span may appear irrelevant by itself, and deciding whether to retain it may require examining other retrieved information. One can evaluate each span's candidacy with the full retrieved context, but this is computationally inefficient as the same text must be processed repeatedly. Pretrained decision model can be used to efficiently evaluate multiple spans simultaneously, allowing each decision to consider the surrounding spans as well. However, our experiments show that their ability to identify relevant evidence deteriorates as the number of simultaneous decisions increases. To address this, we introduce CURATOR, a fine-tuned decision model trained to make reliable evidence-selection decisions over large candidate sets. By training a decision model to select varying numbers of supporting spans from large candidate pools, CURATOR develops the capability to select evidence for RAG while retaining the computational efficiency of joint decision-making. We observe that CURATOR maintains a strong evidence discrimination capability as the number of candidates increases, generalizes across different tasks and document domains, and improves downstream RAG performance, particularly when the available context is limited.
查看此版本解读 →查看此版本原文 ↗