Enregistré dans:
Détails bibliographiques
Auteur principal: Grofsky, Matthew
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.19376
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914052794482688
author Grofsky, Matthew
author_facet Grofsky, Matthew
contents We address temporal failures in RAG systems using two methods on cybersecurity data. A simple recency prior achieved an accuracy of 1.00 on freshness tasks. In contrast, a clustering heuristic for topic evolution failed (0.08 F1-score), showing trend detection requires methods beyond simple heuristics.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Solving Freshness in RAG: A Simple Recency Prior and the Limits of Heuristic Trend Detection
Grofsky, Matthew
Machine Learning
Artificial Intelligence
We address temporal failures in RAG systems using two methods on cybersecurity data. A simple recency prior achieved an accuracy of 1.00 on freshness tasks. In contrast, a clustering heuristic for topic evolution failed (0.08 F1-score), showing trend detection requires methods beyond simple heuristics.
title Solving Freshness in RAG: A Simple Recency Prior and the Limits of Heuristic Trend Detection
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.19376