Signals 4 · free daily AI digest

Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers

Paper recorded by Signals 4 on 2026-09-25 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.CL · 自然语言处理 · first seen 2026-09-28

Abstract

Retrieval-augmented generation (RAG) is often used to address outdated knowledge by providing external evidence. But retrieval helps only when that evidence is still valid. We identify a temporal alignment failure, stale-document poisoning, in which outdated evidence makes a model wrong despite answering correctly without retrieval. We construct a benchmark of 317 verified knowledge reversals acro

Read on arXiv →

#11 most recent of 267 cs.CL papers we have recorded · ↑ newer: Highlight-Then-Summarize: Learning to Compress Evidence for Long-Conte · ↓ older: The Right Information Extraction Pipeline Depends on the Document: Acc
Cite this page: Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers: the #11 most recent of 267 cs.CL papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/stale-document-poisoning-when-outdated-retrieval-overrides-correct-model-answers.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions