English

Solving Freshness in RAG: A Simple Recency Prior and the Limits of Heuristic Trend Detection

Machine Learning 2025-09-25 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2509.19376,
  title  = {Solving Freshness in RAG: A Simple Recency Prior and the Limits of Heuristic Trend Detection},
  author = {Matthew Grofsky},
  journal= {arXiv preprint arXiv:2509.19376},
  year   = {2025}
}