Algorithmic Reflectivity in Large Language Models: Methodological Study of Linguistic Structure in Mentalization
Read the original on arXiv Computation and Language →The study investigates whether large language models (LLMs) can generate mentalization profiles that are structurally coherent with mentalization‑based treatment (MBT) dimensions. Fifty GPT‑4.1 dialogues were produced, and the resulting narrative profiles were rated by five MBT‑trained psychiatrists on evaluative and argumentative coherence across canonical MBT axes and higher‑order dimensions. Ratings showed moderate‑to‑high structural coherence (mean scores 3.63–3.98) with strong interrater reliability (ICC(3,k) 0.60–0.84) and a strong association between evaluative and argumentative coherence (Pearson r 0.826–0.967). A negative control confirmed the specificity of the ratings, and clinicians noted that the outputs were linguistically organized and clinically interpretable, though lacking affective variability and contextual integration.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.