Metraipolis › archive › dc_bc04e7b39e12

C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails — arXiv:2610.34961

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34961
License (as archived)
CC0-1.0
Archived
2026-10-27T07:58:21.299Z
SHA-256 of the archived text
29f1a66923d8bf06a78ee970d028f552f76a62d58ff9bbf77cf72d27e4b1688f
Stable URL of this page
https://metraipolis.com/documento/dc_bc04e7b39e12

How to cite

C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails — arXiv:2610.34961 — arXiv (en), https://arxiv.org/abs/2610.34961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc04e7b39e12 (Metraipolis archive dc_bc04e7b39e12, sha256 29f1a66923d8bf06a78ee970d028f552f76a62d58ff9bbf77cf72d27e4b1688f)
BibTeX
@misc{dcbc04e7b39e12,
  title = {C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails — arXiv:2610.34961},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34961},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc04e7b39e12; sha256 29f1a66923d8bf06a78ee970d028f552f76a62d58ff9bbf77cf72d27e4b1688f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the remarkable capabilities of large language models (LLMs) across diverse applications, they remain vulnerable to generating content that violates safety regulations and policies. To mitigate these risks, LLMs undergo safety alignment; however, they can still be effectively jailbroken. Off-the-shelf guardrail models are commonly deployed to monitor generations, but these models primarily focus on detection rather than ensuring safe decoding of LLM outputs. Moreover, existing efforts lack rigorous safety guarantees, which are crucial for the universal deployment of LLMs and certifiable compliance with regulatory standards. In this paper, we propose a Claim-based Stream Decoding (CSD) algorithm coupled with a statistical risk guarantee framework using conformal analysis. Specifically, our CSD algorithm integrates a stream guardrail model to safeguard sequential claims generated by LLMs and incorporates a backtracking mechanism to revise claims flagged with high safety risks. We provide theoretical guarantees demonstrating that the CSD algorithm achieves the desired generation distribution subject to safety constraints. Furthermore, we introduce a generation risk certification framework and derive a high-probability upper bound on the safety risk of the proposed CSD algorithm. We prove that our method can asymptotically control safety risk to any desired level. Empirical evaluations demonstrate the effectiveness and efficiency of the CSD algorithm compared to state-of-the-art safety decoding approaches. Additionally, we validate the soundness and tightness of the derived safety risk upper bound using realistic data.

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/2610.34961 — 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 2026-10-27T07:55:30.727Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).