arXiv Computation and Language September 28, 2026 By Md Shamim Ahmed, Lukas Galke Poech, Richard R\"{o}ttger

Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers

Read the original on arXiv Computation and Language →

The paper introduces "stale‑document poisoning," a temporal alignment failure where outdated retrieval evidence causes retrieval‑augmented generation models to produce incorrect answers even when the model could answer correctly without retrieval. A benchmark of 317 verified knowledge reversals across medicine, law, software, and platform policy shows that outdated evidence flips 30–37% of Llama and Qwen answers, rising to 66–75% when models are explicitly instructed to trust the document. The study demonstrates that providing explicit validity information and a recency‑aware re‑ranker can substantially reduce poisoning, highlighting the need for models to assess whether retrieved evidence remains applicable.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 13

Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation

arXiv:2607. 09349v1 Announce Type: cross Abstract: Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents.

By Cedric Caruzzo, Donggeun Yoo, Tae Soo Kim

rag fine-tuning benchmarks safety

arXiv AI

Sep 1

Detecting and Repairing Hallucinations in Retrieval-Augmented Generation

arXiv:2608.29307v1 Announce Type: cross Abstract: Language models increasingly answer questions by consulting retrieved documents rather than memory alone, a design now common in search assistants an...

By Sai Krishna Reddy Mulakkayala, Niki van Stein, Aske Plaat

llms rag benchmarks safety

arXiv Computation and Language

Sep 10

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

arXiv:2609.09243v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: i...

By Iliano Fasolino

llms rag efficiency safety

arXiv AI

Sep 23

When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search

arXiv:2609.24101v1 Announce Type: new Abstract: Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive...

By Fred Sun, Shangqi Guo

agents reinforcement-learning safety

Hugging Face Trending Papers

Sep 21

When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search

Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive findings. Deeper retrieval can therefore make a...

agents reinforcement-learning safety

arXiv Computation and Language

4d ago

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification

The paper investigates why retrieval‑based open‑ended evaluation fails in medical fact verification. By creating two detailed taxonomies—one for retrieval‑stage errors across five quality dimensions and another for verifier‑reasoning errors across six steps—the authors automatically label evidence quality and reasoning errors using an LLM‑as‑Judge pipeline. Their large‑scale stress tests across multiple retrieval methods and verifier models show that increasing model size, reasoning effort, source breadth, or medical fine‑tuning does not eliminate these failure modes, indicating fundamental limits of the retrieve‑then‑verify paradigm in open‑ended medical contexts.

By Heyuan Huang, Jirui Dai, Alexandra DeLucia, Sonal Joshi, Mahsa Yarmohammadi, Jie Gao, Bernal Jim\'enez Guti\'errez, Mark Dredze

llms rag fine-tuning safety

One email a morning, machine-written

Related stories

Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation

Detecting and Repairing Hallucinations in Retrieval-Augmented Generation

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search

When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification