paperAugust 2026Unreviewed

SingProbe Technical Report

Singg Team

Abstract

Runtime guardrails are essential for reliable large language model (LLM) deployment, yet existing approaches typically rely on independent, external models that introduce additional inference cost, delayed safety signals, and a capacity mismatch with increasingly capable base models. To address these issues, we introduce SingProbe, a lightweight intrinsic runtime guard that directly reuses hidden states produced during LLM inference and operates alongside autoregressive decoding. Within a unifie

Cite

@misc{singg2026singprobe,
  title = {{SingProbe Technical Report}},
  author = {{Singg Team}},
  year = {2026},
  month = aug,
  eprint = {2608.30703},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/b42aefcf52891422ad5d7a2d53a60611fe663afb}
}