arXiv:2606. 10154v1 Announce Type: new Abstract: Quantized checkpoints are often screened first with quality metrics and only later, if at all, with direct safety tests.
arXiv:2607. 28608v1 Announce Type: new Abstract: Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups.
arXiv:2607. 01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable.
arXiv:2608. 15286v1 Announce Type: cross Abstract: We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated runs, with no LLM in the measurement path, demonstrated on EnterpriseOps-Gym.
arXiv:2607. 01854v1 Announce Type: cross Abstract: Can a platform tell, before deployment, whether an open-weight checkpoint has had its refusal mechanism stripped?
arXiv:2607. 19442v1 Announce Type: cross Abstract: Machine unlearning is commonly evaluated by matching a retrained oracle on trained probes.
arXiv:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
arXiv:2608. 11212v1 Announce Type: new Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read by a protected BF16 gate -- pushes tokens across decision boundaries and flips which experts fire.
arXiv:2607. 22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem.
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
arXiv:2607. 28685v1 Announce Type: new Abstract: Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety.
arXiv:2608. 08944v1 Announce Type: cross Abstract: A failed retrieval-augmented generation (RAG) answer can be consistent with several unseen responses to evidence repair.
arXiv:2607. 09800v2 Announce Type: replace Abstract: Master weights and stochastic rounding bypass invisible stored-weight updates but do not locate lost direct-storage proposals or parameters worth protecting.