Metraipolis › archive › dc_af0ec8fa0289

Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting — arXiv:2610.33103

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33103
License (as archived)
CC0-1.0
Archived
2026-10-27T07:56:26.264Z
SHA-256 of the archived text
352f1d0b93f1f782f332c21fb5a89b6d4088fec84e08921222275e8fd9350f6a
Stable URL of this page
https://metraipolis.com/documento/dc_af0ec8fa0289

How to cite

Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting — arXiv:2610.33103 — arXiv (en), https://arxiv.org/abs/2610.33103 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af0ec8fa0289 (Metraipolis archive dc_af0ec8fa0289, sha256 352f1d0b93f1f782f332c21fb5a89b6d4088fec84e08921222275e8fd9350f6a)
BibTeX
@misc{dcaf0ec8fa0289,
  title = {Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting — arXiv:2610.33103},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33103},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af0ec8fa0289; sha256 352f1d0b93f1f782f332c21fb5a89b6d4088fec84e08921222275e8fd9350f6a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33103. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Prospect theory splits risky choice into three parts: loss aversion, measured by the relative weight of losses to gains, $\lambda$ (e.g., $\lambda = 2$ implies that losses weigh twice as much as gains), diminishing sensitivity to the size of outcomes (i.e., the curvature and linearity of the value function), and the nonlinear weighting of probabilities. I examined whether Large Language Models (LLMs) display the same properties as people by meta-analyzing 102 fitted estimates from 11 studies covering 32 language models. The three components emerge differently. Loss aversion is modest: the pooled $\lambda$ is 1.26 (95% CI 1.06 to 1.46), far below the strongest human meta-analytic estimate ($\lambda = 1.96$) and compatible with more conservative ones (1.07 and 1.31). Matched by design, LLMs are compatible with people when gains and losses are symmetric ($\lambda = 1.15$ against 1.07), but well below them when losses are smaller than gains (1.46 against 2.3), where human loss aversion is strongest. Value functions are close to linear rather than concave under the Tversky-Kahneman method (1.01, against a human value of 0.67), but more concave than in people under the Tanaka method (0.52, against 0.67), so diminishing sensitivity depends on how it is measured. Probability weighting shows a human-like inverse S shape ($\gamma = 0.81$ under Tversky-Kahneman and 0.84 under the Tanaka method), though on few studies. In sum, LLMs show little loss aversion and little diminishing sensitivity, but retain human-like probability distortion, yet these generalizations shift when looking at specific model families and fitting methods.

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); General Economics (econ.GN).
Pagina del lavoro: https://arxiv.org/abs/2610.33103 — 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 2026-10-27T07:55:30.612Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).