# Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing

arXiv: https://arxiv.org/abs/2602.11786 · HTML: https://mlsanity.com/paper/2602.11786/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 11 of 11)

- [AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies](https://mlsanity.com/paper/2407.17436/) (2024)
- [SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types](https://mlsanity.com/paper/2410.21965/) (2024)
- [Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility](https://mlsanity.com/paper/2305.10235/) (2023)
- [Calibrating LLM Confidence by Probing Perturbed Representation Stability](https://mlsanity.com/paper/2505.21772/) (2025)
- [Efficient Prediction of Pass@k Scaling in Large Language Models](https://mlsanity.com/paper/2510.05197/) (2025)
- [Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability](https://mlsanity.com/paper/2411.06535/) (2024)
- [Quantifying perturbation impacts for large language models](https://mlsanity.com/paper/2412.00868/) (2024)
- [Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy](https://mlsanity.com/paper/2503.00269/) (2025)
- [aiXamine: Simplified LLM Safety and Security](https://mlsanity.com/paper/2504.14985/) (2025)
- [The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior](https://mlsanity.com/paper/2512.12066/) (2025)
- [A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models](https://mlsanity.com/paper/2511.00527/) (2025)

## Built on by (most cited first, 1 of 1)

- [AlphaEval: Evaluating Agents in Production](https://mlsanity.com/paper/2604.12162/) (2026)

## Abstract (arXiv)

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety through breadth-oriented evaluation across diverse tasks and risk categories. However, real-world deployment often exposes a different class of risk: operational failures that arise under repeated inference on identical or near-identical prompts rather than from broad task-level underperformance. In high-stakes settings, response consistency and safety under sustained use are therefore critical. We introduce Accelerated Prompt Stress Testing (APST), a depth-oriented evaluation framework inspired by highly accelerated stress testing in reliability engineering. APST repeatedly samples identical prompts under controlled operational conditions (such as decoding temperature) to surface latent failure modes including hallucinations, refusal inconsistency, and unsafe completions. Rather than treating failures as isolated events, APST models them as stochastic outcomes of repeated inference and uses Bernoulli and binomial formulations to estimate per-inference failure probabilities. Applying APST to multiple instruction-tuned LLMs evaluated on AIR-BENCH 2024--derived safety and security prompts, we find that models with comparable shallow-evaluation scores can exhibit substantially different empirical failure rates under repeated sampling. These results show that single-sample or low-depth evaluation can obscure meaningful differences in deployment-relevant reliability. APST complements existing benchmark methodologies by providing a practical framework for estimating failure frequency under sustained use and comparing safety reliability across models and decoding configurations.