Metraipolis › archive › dc_4fcb5b890f4e
Implicit Personality Representations in Humans and LLMs — arXiv:2609.12704
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12704
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:02:52.848Z
- SHA-256 of the archived text
832c40aaa16bb27515d55dbd606d136193ea6e0078c58da9e4ccaad538e3a345- Stable URL of this page
https://metraipolis.com/documento/dc_4fcb5b890f4e
How to cite
Implicit Personality Representations in Humans and LLMs — arXiv:2609.12704 — arXiv (en), https://arxiv.org/abs/2609.12704 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fcb5b890f4e (Metraipolis archive dc_4fcb5b890f4e, sha256 832c40aaa16bb27515d55dbd606d136193ea6e0078c58da9e4ccaad538e3a345)
BibTeX
@misc{dc4fcb5b890f4e,
title = {Implicit Personality Representations in Humans and LLMs — arXiv:2609.12704},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12704},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fcb5b890f4e; sha256 832c40aaa16bb27515d55dbd606d136193ea6e0078c58da9e4ccaad538e3a345},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12704. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A century of psychology has found that the trait words people use to describe one another vary, but the relational structure among those traits, which ones go together and which oppose, is strikingly consistent across raters and cultures. We test whether the LLM (Qwen 2.5-7B-Instruct) reproduces this structure in its internal trait representations. From millions of crowd-sourced personality ratings of fictional characters, we build a human implicit-personality matrix over hundreds of traits; from contrastive model activations, we build a matching matrix over the same traits. The two relational structures align strongly (Mantel r = 0.77), and the agreement holds trait by trait as well as in aggregate. Two dominant axes of the model's trait representations recover the social and intellectual dimensions long known to organize human personality impressions, social warmth and intellectual competence. On held-out dialogue, projecting model activations onto these directions yields personality profiles that agree with human ratings. This work establishes a framework that enables comprehensive, human-grounded comparison between internal model trait geometry and the shared structure of human personality impressions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.12704 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T02:51:27.814Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).