Salvato in:
Dettagli Bibliografici
Autori principali: Schwartz, Shelly, Vasilyev, Oleg, Sawaya, Randy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.20854
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918486543958016
author Schwartz, Shelly
Vasilyev, Oleg
Sawaya, Randy
author_facet Schwartz, Shelly
Vasilyev, Oleg
Sawaya, Randy
contents In realistic retrieval settings with large and evolving knowledge bases, the total number of documents relevant to a query is typically unknown, and recall cannot be computed. In this paper, we evaluate several established strategies for handling this limitation by measuring the correlation between retrieval quality metrics and LLM-based judgments of response quality, where responses are generated from the retrieved documents. We conduct experiments across multiple datasets with a relatively low number of relevant documents (2-15). We also introduce a simple retrieval quality measure that performs well without requiring knowledge of the total number of relevant documents.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How important is Recall for Measuring Retrieval Quality?
Schwartz, Shelly
Vasilyev, Oleg
Sawaya, Randy
Computation and Language
Information Retrieval
In realistic retrieval settings with large and evolving knowledge bases, the total number of documents relevant to a query is typically unknown, and recall cannot be computed. In this paper, we evaluate several established strategies for handling this limitation by measuring the correlation between retrieval quality metrics and LLM-based judgments of response quality, where responses are generated from the retrieved documents. We conduct experiments across multiple datasets with a relatively low number of relevant documents (2-15). We also introduce a simple retrieval quality measure that performs well without requiring knowledge of the total number of relevant documents.
title How important is Recall for Measuring Retrieval Quality?
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2512.20854