Metraipolis › archive › dc_aa04e2d629ff

The psychophysics of affect in large language models — arXiv:2610.40985

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40985
License (as archived): CC0-1.0
Archived: 2026-11-02T04:42:30.484Z
SHA-256 of the archived text: 43d3777d3794890427b939e1f6fcde3d58c60f34087d0f4c02070c73bff1e362
Stable URL of this page: https://metraipolis.com/documento/dc_aa04e2d629ff

How to cite

The psychophysics of affect in large language models — arXiv:2610.40985 — arXiv (en), https://arxiv.org/abs/2610.40985 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa04e2d629ff (Metraipolis archive dc_aa04e2d629ff, sha256 43d3777d3794890427b939e1f6fcde3d58c60f34087d0f4c02070c73bff1e362)

BibTeX

@misc{dcaa04e2d629ff,
  title = {The psychophysics of affect in large language models — arXiv:2610.40985},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40985},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa04e2d629ff; sha256 43d3777d3794890427b939e1f6fcde3d58c60f34087d0f4c02070c73bff1e362},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40985. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Good decisions often require considering how outcomes will feel. Yet large language models (LLMs) increasingly enter decision workflows, despite little being known about how they map outcomes to feelings or use those mappings in choice. We tested how LLMs anticipated gambling or stock-trading outcomes would feel and whether they incorporated these ratings into choice. When outcomes were rated in isolation, ratings exhibited diminishing sensitivity to magnitude, resembling human value functions; but models rated gains more intensely than equivalent losses, an inversion of canonical loss aversion we call silicon gain amplification. When outcomes were rated together, enabling direct comparison, ratings linearised. In choice, the gain-loss asymmetry largely disappeared, and models' own ratings did not reliably explain their choices better than monetary utility did. These findings reveal malleable mappings from outcomes to affect, raising questions about whether and how agentic LLMs should incorporate anticipated feelings into decisions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.40985 — 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 2026-11-02T04:42:12.333Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).