The paper challenges the assumption that large language models (LLMs) produce deterministic safety responses by examining how random seeds and temperature settings affect refusal decisions. Across four instruction‑tuned models and 876 harmful prompts, 18‑28% of prompts flipped between refusal and compliance depending on sampling configuration, with higher temperatures reducing decision stability. The authors introduce a Safety Stability Index (SSI) and recommend multi‑sample evaluation protocols that account for stochastic variation rather than relying on single‑shot tests.
arXiv:2606. 26185v1 Announce Type: new Abstract: LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions.
arXiv:2606. 29581v1 Announce Type: cross Abstract: Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details.
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.
Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details. This leaves a practical uncertainty: does a model that is safe at FP16 and greedy decoding remain safe after it is quantized and sampled stochastically, or do the two deployment knobs amplify one another?
arXiv:2609.19072v1 Announce Type: cross Abstract: Large language models are increasingly used for content moderation, but most evaluations still report aggregate accuracy on individual benchmarks. We...
arXiv:2606. 25097v1 Announce Type: new Abstract: Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify, raising a concrete safety question: at temperature zero, can draft-side behavior leak into safety-scored outputs?
The study examines how two small instruction‑tuned language models, Qwen2.5‑1.5B and Llama‑3.2‑1B, respond to user pushback on TriviaQA. When initially correct, the models flip to a wrong answer in about 42–43% of cases, with the effectiveness of different pushback styles varying by model. Attempts to decode capitulation from the pre‑response residual stream fail under a rigorous validation protocol, revealing overfitting and a measurement hazard that underestimates capitulation by 18–24 percentage points.
arXiv:2607. 01951v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat from established consensus when a user signals doubt -- drifting toward a false balance that treats settled science as one view among several.
arXiv:2511. 00382v2 Announce Type: replace-cross Abstract: Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks.
arXiv:2607. 01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task.
arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.
arXiv:2607. 08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise.