The paper introduces Bounded Continuation Analysis (BCA), a method that models autoregressive language model generation as a stochastic process over token prefixes to compute the finite‑horizon probability of reaching a harmful continuation. BCA builds a bounded continuation tree, labels terminal continuations with a semantic harm evaluator, and uses exact probabilistic model checking to estimate harmful reachability. Unlike traditional attack success rate (ASR) metrics that only assess sampled outputs, BCA reveals hidden harmful paths that may coexist with safe responses, enabling more precise red‑team targeting across instruction‑tuned LLMs and JailbreakBench behaviors.
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.
arXiv:2606. 05614v1 Announce Type: new Abstract: 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.
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.
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:2605.13043v3 Announce Type: replace Abstract: Diffusion Language Models(DLMs) provide a promising alternative to autoregressive language models through iterative denoising and bidirectional gen...
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
arXiv:2604. 22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale.
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.
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.
arXiv:2405.18540v3 Announce Type: replace-cross Abstract: Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of larg...
arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
arXiv:2508. 20697v4 Announce Type: replace Abstract: As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning.