Semantic Recall for Vector Search

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kuffo, Leonardo, Tsakalidou, Ioanna, De Viti, Roberta, Angel, Albert, Iša, Jiří, Lenhardt, Rastislav
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911614594187264
author Kuffo, Leonardo
Tsakalidou, Ioanna
De Viti, Roberta
Angel, Albert
Iša, Jiří
Lenhardt, Rastislav
author_facet Kuffo, Leonardo
Tsakalidou, Ioanna
De Viti, Roberta
Angel, Albert
Iša, Jiří
Lenhardt, Rastislav
contents We introduce Semantic Recall, a novel metric to assess the quality of approximate nearest neighbor search algorithms by considering only semantically relevant objects that are theoretically retrievable via exact nearest neighbor search. Unlike traditional recall, semantic recall does not penalize algorithms for failing to retrieve objects that are semantically irrelevant to the query, even if those objects are among their nearest neighbors. We demonstrate that semantic recall is particularly useful for assessing retrieval quality on queries that have few relevant results among their nearest neighbors-a scenario we uncover to be common within embedding datasets. Additionally, we introduce Tolerant Recall, a proxy metric that approximates semantic recall when semantically relevant objects cannot be identified. We empirically show that our metrics are more effective indicators of retrieval quality, and that optimizing search algorithms for these metrics can lead to improved cost-quality tradeoffs.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20417
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Semantic Recall for Vector Search
Kuffo, Leonardo
Tsakalidou, Ioanna
De Viti, Roberta
Angel, Albert
Iša, Jiří
Lenhardt, Rastislav
Information Retrieval
Artificial Intelligence
We introduce Semantic Recall, a novel metric to assess the quality of approximate nearest neighbor search algorithms by considering only semantically relevant objects that are theoretically retrievable via exact nearest neighbor search. Unlike traditional recall, semantic recall does not penalize algorithms for failing to retrieve objects that are semantically irrelevant to the query, even if those objects are among their nearest neighbors. We demonstrate that semantic recall is particularly useful for assessing retrieval quality on queries that have few relevant results among their nearest neighbors-a scenario we uncover to be common within embedding datasets. Additionally, we introduce Tolerant Recall, a proxy metric that approximates semantic recall when semantically relevant objects cannot be identified. We empirically show that our metrics are more effective indicators of retrieval quality, and that optimizing search algorithms for these metrics can lead to improved cost-quality tradeoffs.
title Semantic Recall for Vector Search
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2604.20417