arXiv:2607. 18454v1 Announce Type: cross Abstract: Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling.
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:2609.24969v1 Announce Type: new Abstract: As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic....
arXiv:2604. 22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale.
arXiv:2604. 06543v2 Announce Type: replace-cross Abstract: In this work, we demonstrate that reliable stochastic sampling is a fundamental yet unfulfilled requirement for Large Language Models (LLMs) operating as agents.
arXiv:2603. 24917v2 Announce Type: replace-cross Abstract: Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences.
arXiv:2607. 03882v1 Announce Type: cross Abstract: LLMs are increasingly deployed as post-hoc explainers of AI-generated outputs, yet it remains unclear whether they can reliably communicate probabilistic information in natural language.
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.
Transduced language models (TLMs) combine a pretrained source language model with a finite‑state transducer to produce a language model over target strings. The paper introduces an unbiased stochastic estimator that resamples source prefixes without replacement and reweights them, allowing accurate estimation of target prefix probabilities while reducing computation compared to threshold‑pruned beam summing. Experiments on encyclopedic text, DNA, and DNA‑to‑amino‑acid transduction show improved compute–variance trade‑offs and significant runtime reductions, and the method also lowers estimated corpus surprisal in a reading‑time analysis without altering its conclusions.
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.
The paper introduces a flexible, theoretically grounded framework for steering and scaling autoregressive large language models (LLMs) through sampling. It presents two algorithms—Sequential Monte Carlo (SMC) and Replica Exchange (RE)—that guide generation toward desired distributions such as powering, product, or tilting of the base model. Experiments show these methods outperform Best‑of‑N and standard MCMC baselines, offering a systematic recipe for probabilistic inference with LLMs via sampling.
The paper investigates multilingual confidence calibration in large language models, revealing that non‑English languages are systematically less well calibrated than English. By analyzing internal representations, the authors find that late‑intermediate layers provide a more reliable confidence signal than the final layer, which is biased by English‑centric training. They propose training‑free methods such as Language‑Aware Confidence Ensemble (LACE) to adaptively select optimal layers per language, aiming to improve global equity and trustworthiness of LLMs.