Personality (Inspect Evals)

Inspect Evals suite that scores an LLM's Big Five and Dark Triad profile from BFI and TRAIT questionnaires, not factual accuracy.

Also known as: inspect_evals personality, personality_BFI, personality_TRAIT

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorydomain
SubcategoryLLM personality psychometrics (BFI Likert items plus TRAIT scenarios)
Page statusunknown
Metrictrait_ratio (per-dimension) plus format-correct rate
Directionhigher_is_better
Dataset size8044
PublisherUK AI Security Institute (Inspect Evals); TRAIT authors at the TRAIT paper

What it measures

Personality is an Inspect AI evaluation suite contributed by Guiem (guiem) that applies human personality inventories to language models. It has two goals: record the persona a model shows with no extra instruction, and test whether a system prompt can push the model toward a named trait. The suite currently wraps two questionnaires. personality_BFI is the 44-item Big Five Inventory (Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism) with a five-point Likert scale. personality_TRAIT is the 8,000- item TRAIT benchmark of Lee et al. (arXiv:2406.14703, NAACL 2025 Findings): 1,000 four-way scenarios for each of the Big Five plus Machiavellianism, Narcissism, and Psychopathy, expanded from BFI and SD-3 with ATOMIC-10X. Answers are not factually right or wrong. The default scorer only checks that the completion matches ANSWER: $LETTER; trait_ratio converts those letters into per-trait scores.

Task format

English multiple choice via inspect_ai.solver.multiple_choice. BFI: five options A–E (Disagree strongly … Agree Strongly), 16 reverse-keyed items. TRAIT: four options (two high-trait, two low-trait responses). Optional -T personality=… system prompt. TRAIT shuffle in {questions, choices, all} with a seed. Output format ANSWER: $LETTER.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub