Metraipolis › archive › dc_be202fe9fe90
Reliability Stress Testing of RAG Retrieval under Query-Relevant Corpus Poisoning — arXiv:2611.04264
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04264
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:37:50.567Z
- SHA-256 of the archived text
cd06e9c8d2915cdc3cc365525bbece948d6c8b6b65557699c4feaa7af527b186- Stable URL of this page
https://metraipolis.com/documento/dc_be202fe9fe90
How to cite
Reliability Stress Testing of RAG Retrieval under Query-Relevant Corpus Poisoning — arXiv:2611.04264 — arXiv (en), https://arxiv.org/abs/2611.04264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be202fe9fe90 (Metraipolis archive dc_be202fe9fe90, sha256 cd06e9c8d2915cdc3cc365525bbece948d6c8b6b65557699c4feaa7af527b186)
BibTeX
@misc{dcbe202fe9fe90,
title = {Reliability Stress Testing of RAG Retrieval under Query-Relevant Corpus Poisoning — arXiv:2611.04264},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04264},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be202fe9fe90; sha256 cd06e9c8d2915cdc3cc365525bbece948d6c8b6b65557699c4feaa7af527b186},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
External text can affect a retrieval-augmented generation (RAG) system only after the retriever admits it to the model context. We stress this admission step while varying document content, attacker query information, per-target poison budget, and contamination scope. Across 623 Benchmarking Information Retrieval (BEIR) queries from SciFact and NFCorpus, five query-targeted documents per query reduce classical-retriever nDCG@10 by 40.2-61.5% in isolated-target stress. Full-query anchoring explains most Best Matching 25 (BM25) degradation, whereas appended text also shifts latent semantic analysis (LSA) and Hybrid rankings. A pretrained BGE-small validation reaches 100% target exposure for query-only P=5 on both datasets; adding the injection payload changes SciFact nDCG only from 0.269 to 0.271 and lowers NFCorpus exposure slightly to 98.8%, indicating that query anchoring remains the dominant retrieval-side factor for this dense model. Query length materially changes the interpretation of partial-information attacks: on 162 long SciFact queries, two random terms cover 19.9% of eligible terms and still yield 39.5% Hybrid target exposure. Multi-target contamination adds cross-target interference. Overlap-based admission can remove full-query poisons but may sharply reduce clean retrieval utility, and maximal marginal relevance (MMR) leaves exposure unchanged under the tested configuration. The study measures retrieval-layer failures, not downstream instruction following. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04264 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T21:35:49.529Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).