arXiv:2604. 22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper introduces RareTrap, a framework that estimates the probability of severe behaviors in black‑box large language models. RareTrap constructs a geometry‑aware mapping from a low‑dimensional latent space into token‑embedding space using a surrogate LLM, creating an explicit and reproducible distribution over input prompts. By applying a response‑level performance function and sequential rare‑event simulation, RareTrap concentrates evaluations on increasingly severe behaviors while preserving probability, enabling estimation of such behaviors with as few as 200 evaluations across multiple open‑weight and frontier models.
arXiv:2607. 18295v1 Announce Type: new Abstract: We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability of harmful behavior to zero in modern large language models.
arXiv:2608. 10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs.
arXiv:2607. 20286v1 Announce Type: cross Abstract: We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt.
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.
We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem.