LATIDIA · Investigación

Rastreo de inferencias psicométricas en modelos de lenguaje grandes

arXiv:2611.12937v1 Tipo de anuncio: nuevo Resumen: ¿Los modelos de lenguaje grandes representan construcciones psicológicas internamente, o solo generan salidas que se asemejan a la estructura psicométrica? Abordamos esta pregunta usin

La noticia

arXiv:2611.12937v1 Announce Type: new Abstract: Do large language models represent psychological constructs internally, or do they only generate outputs that resemble psychometric structure? We address this question using a cross-persona paradigm across 14 model variants from two families (Llama 3 and Qwen 2.5, 0.5B-14B, base and instruct). Given responses on one psychological scale from real individuals (N = 272 Taiwanese university students), models predict responses on six other scales. At the behavioral level, larger variants reproduce and amplify human cross-scale correlations; amplification persists after correcting the seven-scale human correlations for measurement attenuation. We then examine whether this structure is reflected internally. Contrastive direction analysis finds geometry aligned with the human