English(EN) The psychophysics of affect in large language models

研究发现大语言模型在情感评级中表现出“硅增益放大”

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

一项发表在arXiv上的新研究探讨了大语言模型（LLMs）如何在决策过程中感知和融入“感受”或情感，特别是在赌博或股票交易等场景中。研究人员发现，大语言模型表现出一种称为“硅增益放大”的现象，即它们对收益的评级比对等价损失的评级更强烈，这与人类的损失厌恶形成对比。然而，当模型直接比较结果时，这种情感不对称性会减弱，并且它们自我评级的情感并不比客观的货币效用更能一致地预测其选择。这些发现引发了关于代理型大语言模型应如何将预期情感纳入其决策过程的重要问题。 AI

影响引发了关于大语言模型应如何将情感纳入决策过程的疑问，影响了未来代理型AI的发展。

排序理由发表在arXiv上的学术论文，详细介绍了关于大语言模型行为的新发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发表在arXiv上的学术论文，详细介绍了关于大语言模型行为的新发现。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Joseph Marks (NatWest Group, London, UK), Marius C. Vollberg (University of Zurich, Zurich, Switzerland, Swiss Center for Affective Sciences, Geneva, Switzerland) · 2026-11-02 05:00

The psychophysics of affect in large language models

arXiv:2610.40985v1 Announce Type: cross Abstract: 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 c…

本文如何被排名

报道来源 [1]

The psychophysics of affect in large language models

相关实体

相关话题