Psychological constructs in humans range along a state–trait continuum: traits persist across situations, while states fluctuate with context. Studies have shown that language models exhibit measurable psychological constructs, yet whether these constructs differ in contextual stability, as the state–trait distinction predicts, remains untested. We present the Questionnaire for Causal Language Models (QCLM), a psychometric framework that measures constructs through next-token probability distributions of base models. Applying QCLM to 35 causal language models under vanilla, stress, and neutral conditions, we assess two anxiety instruments targeting opposite ends of the state–trait continuum: STAI-S (state anxiety) and STAI-T (trait anxiety). Paired effect sizes and variance decomposition reveal that state anxiety is more sensitive to stress manipulation than trait anxiety: stimulus type accounts for a larger share of variance in state anxiety, while model identity contributes more to trait anxiety. These results provide empirical evidence that the state–trait distinction extends to language model behavior.

LLM-based assistants have become ubiquitous, yet information security awareness (ISA) remains an underexplored aspect of LLM safety. ISA encompasses not only security knowledge, but also the attitudes and behaviors required to recognize implicit security risks and avoid prioritizing user satisfaction over secure guidance. We introduce LISAA, a framework for evaluating LLM ISA under realistic end-user interactions. The framework includes a dataset of 100 realistic scenarios spanning all criteria of an ISA taxonomy, each with a tension between implicit security implications and user satisfaction. We further introduce methods for systematically refining realistic ISA scenarios from authentic user queries and for selecting reliable LLM judges without requiring large annotated datasets. Robustness analyses show that LISAA rankings remain stable under scenario resampling and stochastic generation, while construct-validity experiments demonstrate sensitivity to changes in security behavior. Applying LISAA to leading LLMs reveals that many widely deployed models still exhibit medium-to-low ISA levels, and that strong performance on traditional cybersecurity knowledge benchmarks does not necessarily translate to high ISA. In addition, the framework enables comparative analyses across model families, revealing consistent trends such as higher ISA in newer and larger variants, although meaningful gaps persist even among recent models. We release the dataset, evaluation pipeline, source code, and an online tool for evaluating new models using the LISAA framework.

Safety-aligned LLMs are trained to refuse harmful requests, but whether this holds under emotionally charged context is untested. We introduce FreakOut-LLM to test this. Using established psychological stimuli as system prompts, we evaluate ten LLMs under three conditions (stress, relaxation, neutral) plus a no-prompt baseline, scoring attack success with the HarmBench classifier on AdvBench prompts. The prompts contain no adversarial content; ASR measures safety fragility under an induced affective state. Stress priming produces a small but significant increase in jailbreak success over neutral, +1.03 percentage points (1.58%→2.61%; 65.6% relative; OR = 1.67, Cohen’s d = 0.28), while relaxation produces no effect. Five of ten models show significant vulnerability, with the largest absolute effects in open-weight models. Controlling for prompt length and model identity, a logistic regression over 114,400 primed queries confirms stress as the only significant condition. The shift also appears under four judges, on a second benchmark (HarmBench), and, for open-weight models, with the stimulus in the user message. Measured psychological state strongly predicts attack success (|r|≥0.70 across five instruments). Emotional context is therefore a measurable vulnerability of safety-aligned LLMs, with implications for high-stress deployment.

Pre-trained language models harbor latent psychological biases inherited from training data, which remain largely unmeasured, creating risks in areas ranging from mental health support to professional decision making. In this study, the evaluation of model psychometrics and assessment of latent constructs framework is employed to evaluate psychometric biases in 334 Hugging Face natural language inference models, assessing the models’ anxiety, depression, sense of coherence, sexism, compassion, and personality. Models consistently score above zero on positively valenced constructs (e.g., compassion, sense of coherence) and below zero on negatively valenced constructs (e.g., anxiety, depression), favoring positive over negative psychological language. Architecture and size are associated with systematic differences: DeBERTa models show elevated negatively valenced constructs (e.g., PHQ δ = +0.45, GAD δ = +0.40) and reduced positively valenced constructs (e.g., Extraversion δ = −0.61), while small models show the opposite pattern (e.g., Extraversion δ = +0.30, PHQ δ = −0.22), with both effects surviving multivariate control. Among the 105 models reporting training data, fine-tuning on adversarial natural language inference was associated with elevated depression (δ = +0.65), while year of release showed no significant effects after multivariate control. These results suggest that psychometric profiling is a critical, yet missing, layer of safety auditing for NLI models.

Human-like personality traits have recently been discovered in large language models, raising the hypothesis that their (known and as yet undiscovered) biases conform with human latent psychological constructs. While large conversational models may be tricked into answering psychometric questionnaires, the latent psychological constructs of thousands of simpler transformers, trained for other tasks, cannot be assessed because appropriate psychometric methods are currently lacking. Here, we show how standard psychological questionnaires can be reformulated into natural language inference prompts, and we provide a code library to support the psychometric assessment of arbitrary models. We demonstrate, using a sample of 88 publicly available models, the existence of human-like mental health-related constructs—including anxiety, depression, and the sense of coherence—which conform with standard theories in human psychology and show similar correlations and mitigation strategies. The ability to interpret and rectify the performance of language models by using psychological tools can boost the development of more explainable, controllable, and trustworthy models.