שאלוני פסיכומטריים לבני אדם טומן טריקים לגבי התנהגות LLM

תקציר מקורי באנגליתarXiv:2509.10078v5 Announce Type: replace Abstract: We examine whether human psychometric questionnaires can serve as reliable tools for characterizing and predicting LLM behavior in everyday user interactions. We analyze eight open-source LLMs by comparing their value and personality profiles derived from two different methods: Likert self-reports on established questionnaires (PVQ-40/21 and BFI-44/10) and generation probabilities over value-laden responses to everyday user queries. The two profiles diverge substantially. Within-construct item consistency, often cited as evidence of stable LLM dispositions, disappears in generation probabilities. We find that established questionnaire items contain explicit lexical cues that allow models to recognize the target construct and respond in al