---
title: "Nothing Left Behind: Finding Evidence from a Large Randomized Evaluation Corpus"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.36910v1"
permalink: "https://feed.astralor.com/items/itm_2c60ee3aa26b10653b6301ea"
published: "2026-10-27T09:40:24.000Z"
score: 53
channel: "tech"
tags: ["RAG","Nothing Left Behind","Finding Evidence","Large Randomized Evaluation","Corpus Many","Many","Those"]
---

# Nothing Left Behind: Finding Evidence from a Large Randomized Evaluation Corpus

## 速览

Many AI systems need to find every relevant items in a large collection and then organize what they found. The standard way to do this is to tag each item with labels from a curated vocabulary and search on those labels…

## 关键点

- Many AI systems need to find every relevant items in a large collection and then organize what they found.
- The standard way to do this is to tag each item with labels from a curated vocabulary and search on those labels.
- Those labels are useful for organizing results, but searching on them misses items that do not fit a label and returns too much when labels are broad.

## 全文

Many AI systems need to find every relevant items in a large collection and then organize what they found. The standard way to do this is to tag each item with labels from a curated vocabulary and search on those labels. Those labels are useful for organizing results, but searching on them misses items that do not fit a label and returns too much when labels are broad. We compare this approach with an embedding-based approach: find candidates by meaning using text embeddings, then have a language model keep only the relevant ones. In a corpus of 7,354 randomized trials, label search found 45% of the evidence a systematic review would include, while the new approach found 92%, at a cost per query that rises with search depth. These results support a two-stage architecture that combines broad candidate retrieval with query-specific evidence filtering.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_2c60ee3aa26b10653b6301ea