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.
By Elsayed Eshra, Ali Al-Lawati, Dongwon Lee, Suhang Wang
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.
By Aryan Dutt, Rui Mao, Anupam Chattopadhyay
arXiv:2608. 10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs.
By Xinzhe Huang, Biwu Yao, Kedong Xiu, Mengnan Zhao, Di Wang, Puning Zhao, Tianhang Zheng
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.
By Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate
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.
By Zhouyuan Ma, Yutao Wu, Hanxun Huang, Xiang Zheng, Xiao Liu, Yixin Cao, Zuxuan Wu, Xingjun Ma, Yu-Gang Jiang
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.
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.
By Nikita Y. Parulekar, Anqi Liu
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....
By Hanming Yang, Daksh Mittal, Jing Dong, Hongseok Namkoong
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
By Jason Vega, Gagandeep Singh
arXiv:2606. 04778v1 Announce Type: new Abstract: Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs.
By Kyungmin Park, Taesup Kim
arXiv:2606. 04168v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is fragile in part because it is often shallow: fine-tuning mainly reshapes the model's behavior near the first few output tokens.
By Bochen Lyu, Yiyang Jia, Xiaohao Cai, Zhanxing Zhu
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.