Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses

Excerpt

arXiv:2608.17810v1 Announce Type: new Abstract: The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitly assuming that AI and humans employ similar underlying cognitive constructs. Challenging this assumption, we investigate whether the latent factors governing LLM performance carry the same substantive, human-interpretable meaning as the cognitive constructs governing human learners. Using responses from humans and six LLMs across quantitative reas