Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles
For researchers and developers of personalized AI agents, ASPECT offers an inspectable, training-free method to model communication style, but results are preliminary with moderate alignment and high variance.
ASPECT generates communication profiles from behavioral evidence without per-person training, achieving moderate alignment with self-assessments and preferred over baselines in aggregate, though with substantial individual variation.
AI agents that communicate on behalf of individuals need to capture how each person actually communicates, yet current approaches either require costly per-person fine-tuning, produce generic outputs from shallow persona descriptions, or optimize preferences without modeling communication style. We present ASPECT (Automated Social Psychometric Evaluation of Communication Traits), a pipeline that directs LLMs to assess constructs from a validated communication scale against behavioral evidence from workplace data, without per-person training. In a case study with 20 participants (1,840 paired item ratings, 600 scenario evaluations), ASPECT-generated profiles achieved moderate alignment with self-assessments, and ASPECT-generated responses were preferred over generic and self-report baselines on aggregate, with substantial variation across individuals and scenarios. During the profile review phase, linked evidence helped participants identify mischaracterizations, recalibrate their own self-ratings, and negotiate context-appropriate representations. We discuss implications for building inspectable, individually scoped communication profiles that let individuals control how agents represent them at work.