Metraipolis › archive › dc_3205a17593a5

Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse — arXiv:2611.10418

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.10418
License (as archived): CC0-1.0
Archived: 2026-11-10T18:40:58.365Z
SHA-256 of the archived text: 5f06ffab7b57d6c2e4f506dc9518ef6e4d895786416e54c305cccec90ae0a0c2
Stable URL of this page: https://metraipolis.com/documento/dc_3205a17593a5

How to cite

Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse — arXiv:2611.10418 — arXiv (en), https://arxiv.org/abs/2611.10418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3205a17593a5 (Metraipolis archive dc_3205a17593a5, sha256 5f06ffab7b57d6c2e4f506dc9518ef6e4d895786416e54c305cccec90ae0a0c2)

BibTeX

@misc{dc3205a17593a5,
  title = {Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse — arXiv:2611.10418},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10418},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3205a17593a5; sha256 5f06ffab7b57d6c2e4f506dc9518ef6e4d895786416e54c305cccec90ae0a0c2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Semantic response caching reuses a cached response for a semantically similar query to improve LLM inference efficiency. However, query similarity alone can lead to unsafe reuse when safety conditions change. Existing approaches improve cache safety through stricter similarity checks, context-aware validation, or response verification, yet they may still miss safety conflicts between the cached response and the new request or introduce unnecessary verification overhead. We argue that safe and efficient semantic caching requires a reuse policy that makes the cached response's safety conditions explicit and uses them to guide the reuse decision with a balance between safety and utility. In this paper, we propose SafeCache, a safety-aware framework that separates candidate retrieval from safety approval and formulates semantic response reuse as a safety-conditioned routing problem. SafeCache matches each cached-response condition against the new request and aggregates the per-condition mismatches into an overall risk score. A separate contradiction guard prevents explicit conflicts from being diluted by strong matches. It further estimates matching uncertainty and calibrates the routing policy under a required unsafe-reuse target and a verifier-call budget to choose among direct reuse, selective verification, or regeneration. Experiments show that SafeCache achieves the better safety-utility trade-off among the evaluated baselines, enabling safer response reuse at comparable cache utility.

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/2611.10418 — 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 2026-11-10T18:37:37.490Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).