arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv:2607. 01153v1 Announce Type: cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused appropriately, complied with a policy, resisted an embedded command, or misreported progress in an agentic task.
arXiv:2608. 05086v1 Announce Type: new Abstract: Language models differ in how safely they behave and these differences are measured by safety benchmarks.
arXiv:2605. 23055v2 Announce Type: replace-cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results.
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.
The paper introduces "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.
The paper investigates whether existing AI safety benchmarks, designed for large language models, are suitable for evaluating small language models (SLMs). By testing five benchmark suites on 26 open‑source SLMs with a unified scoring rubric, the authors find that ambiguous judgments dominate, especially for complex prompts and certain architectures. This ambiguity, linked to factors like lexical density and output perplexity, undermines the reliability of aggregate leaderboards and reveals a confound between model capability and perceived safety.
arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.
The paper investigates Self‑Generated Text Recognition (SGTR), the ability of large language models (LLMs) to identify their own outputs. By evaluating 13–21 models across 6 experimental designs, it shows that SGTR accuracy varies with evaluation format, conversation structure, and task domain, and that a quality‑heuristic bias dominates results. The study also finds that fine‑tuning for SGTR in one setting can generalize to others and may cause models to prefer their own outputs when judging, highlighting potential safety concerns.
arXiv:2607. 28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples.
arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.
arXiv:2608. 06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness.
The paper demonstrates that Item Response Theory (IRT) can uncover meaningful structure in safety benchmarks for language models, allowing adaptive item selection to approximate full benchmark rankings with Spearman’s ρ > 0.90 while cutting evaluation costs by at least 80% and up to 99.9% on some suites. It also proposes a static method to extract a small, informative subset of items that can be reused across models, achieving 80–99.8% cost savings. These findings show that psychometric techniques can make safety evaluation more efficient without sacrificing ranking accuracy.