{"version":1,"type":"story","url":"https://digestai.news/story/study-finds-llms-show-modest-loss-aversion","json":"https://digestai.news/story/study-finds-llms-show-modest-loss-aversion.json","markdown":"https://digestai.news/story/study-finds-llms-show-modest-loss-aversion.md","slug":"study-finds-llms-show-modest-loss-aversion","headline":"Study finds LLMs show modest loss aversion","summary":"The paper meta‑analyzes 102 estimates from 11 studies covering 32 language models to assess prospect theory components in large language models. The pooled loss‑aversion parameter λ is 1.26 (95 % CI 1.06 to 1.46), lower than the strongest human estimate of 1.96 and closer to conservative estimates of 1.07 and 1.31. Value‑function curvature is nearly linear (1.01) versus a human value of 0.67, though it is more concave under the Tanaka method (0.52). Probability weighting follows a human‑like inverse‑S shape with γ values of 0.81 and 0.84 under two measurement methods. The study concludes that LLMs exhibit little loss aversion and diminishing sensitivity but retain human‑like probability distortion, with variations across model families and fitting methods.","keyPoints":["Pooled λ = 1.26 (95% CI 1.06–1.46) for loss aversion","Value function nearly linear at 1.01 versus human 0.67","Probability weighting γ ≈0.81–0.84 inverse‑S shape"],"whyItMatters":"Understanding how large language models process risk and uncertainty helps gauge their decision‑making behavior and potential biases in applications such as finance, health, or policy advice.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-10-27T04:00:00Z","updatedAt":"2026-10-27T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Prospect Theory in Large Language Models: A Meta-Analysis of Loss Aversion, Diminishing Sensitivity, and Probability Weighting","url":"https://arxiv.org/abs/2610.33103","publishedAt":"2026-10-27T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Study finds LLMs show modest loss aversion\", 27 October 2026, https://digestai.news/story/study-finds-llms-show-modest-loss-aversion","publisher":"Digest AI","title":"Study finds LLMs show modest loss aversion","datePublished":"2026-10-27T04:00:00Z","url":"https://digestai.news/story/study-finds-llms-show-modest-loss-aversion"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}