Metraipolis › archive › dc_b3758aea6007

SingProbe Technical Report — arXiv:2608.30703

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30703
License (as archived)
CC0-1.0
Archived
2026-10-17T07:52:57.958Z
SHA-256 of the archived text
957aeb11e6c9d221a4e60bfee71febe5ccd3ffbda5fa28838014fc7179ca5c7a
Stable URL of this page
https://metraipolis.com/documento/dc_b3758aea6007

How to cite

SingProbe Technical Report — arXiv:2608.30703 — arXiv (en), https://arxiv.org/abs/2608.30703 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3758aea6007 (Metraipolis archive dc_b3758aea6007, sha256 957aeb11e6c9d221a4e60bfee71febe5ccd3ffbda5fa28838014fc7179ca5c7a)
BibTeX
@misc{dcb3758aea6007,
  title = {SingProbe Technical Report — arXiv:2608.30703},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30703},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3758aea6007; sha256 957aeb11e6c9d221a4e60bfee71febe5ccd3ffbda5fa28838014fc7179ca5c7a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30703. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present SingProbe, an open intrinsic guardrail framework for generation-time monitoring of LLMs. Intrinsic guardrails reuse hidden states already produced by the base model during autoregressive decoding, rather than relying on an independent model to repeatedly process generated text. While this route has been explored in industrial systems, the community lacks a broadly reusable open stack that combines cross-model guard adaptations, unified training methods, serving integrations, and systematic evaluation resources. SingProbe is designed to provide this missing layer and uses a lightweight probe to continuously produce query-intent, response-safety, and hallucination-risk signals during decoding. This report describes the full intrinsic-guardrail stack: training methods, serving integrations with SGLang and vLLM, and adapted guard models for 29 open-source base models across diverse families and scales. We also introduce SingStreamBench, a benchmark that measures whether streaming guardrails remain inactive on benign prefixes while promptly detecting emerging unsafe content. Across evaluations of safety, streaming detection, hallucination detection, false-positive robustness, online monitoring, and runtime overhead, SingProbe provides performance competitive with, and in several settings stronger than, state-of-the-art standalone guardrails and specialized hallucination detectors, while adding less than 0.5% serving overhead in our implementation. Beyond passive monitoring, we show that intrinsic guard signals can guide constrained decoding and selectively activate medical-risk interventions in SingProbe-Med. By open-sourcing our infrastructure, training methods, and model adaptations, we aim to facilitate the broader adoption and deployment of intrinsic guardrails, as well as further research in this direction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.30703 — 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 2026-10-17T07:28:26.900Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).