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

arXiv:2610.36910v1 Announce Type: new Abstract: 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.

Related

• Evidence-Gated Bilingual RAG for Reliable Consumer Banking Search
• From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation
• Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage
• Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval
• WARP: Wasserstein-Aligned RAG for Population Opinions

Source: arXiv cs.CL | 2026-10-28