Metraipolis › archive › dc_f04e7dffebac

More Than Just Style: Benchmarking Personality Influence in Large Language Models — arXiv:2611.12392

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.12392
License (as archived): CC0-1.0
Archived: 2026-11-10T18:44:50.018Z
SHA-256 of the archived text: 8c23610f6fd8099ec3c85276c2400b6cb61273531c9f52ec3ee5ed4c99b5c9df
Stable URL of this page: https://metraipolis.com/documento/dc_f04e7dffebac

How to cite

More Than Just Style: Benchmarking Personality Influence in Large Language Models — arXiv:2611.12392 — arXiv (en), https://arxiv.org/abs/2611.12392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f04e7dffebac (Metraipolis archive dc_f04e7dffebac, sha256 8c23610f6fd8099ec3c85276c2400b6cb61273531c9f52ec3ee5ed4c99b5c9df)

BibTeX

@misc{dcf04e7dffebac,
  title = {More Than Just Style: Benchmarking Personality Influence in Large Language Models — arXiv:2611.12392},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12392},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f04e7dffebac; sha256 8c23610f6fd8099ec3c85276c2400b6cb61273531c9f52ec3ee5ed4c99b5c9df},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In addition to the effects of explicit input prompts and instructions, large language model outputs are influenced by underlying behavioral preferences similar to human personality tendencies. These tendencies can affect how models interpret situations and make decisions. However, their influence is difficult to disentangle from the effects of model capabilities and instructions. Therefore, we introduce SPACE, a benchmark framework combining a controlled evaluation protocol with complementary datasets for personality verification, capability assessment, and hierarchical situational tasks. Controlled comparisons across guidance conditions help distinguish personality influence from measured capability changes and immediate instruction effects. Experimental results demonstrate that although prompting can shift generation style, models' internal personality tendencies are persistent and not readily overridden by opposing instructions. Furthermore, these underlying tendencies have an observable influence on LLM task performance, highlighting the need for greater attention to these characteristics and potential applications. Training code and SPACE benchmark specifications are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.12392 — 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 2026-11-10T18:37:52.453Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).