English(EN) Out-of-Distribution Generalization of Risk Aversion in Language Models

AI风险规避可跨越巨大利益进行泛化，但尚不可靠

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-07 04:00

研究人员开发了一个新的基准测试RiskAverseOOD，用于测试语言模型如何将风险规避从低风险情景泛化到高风险情景。使用Qwen3、Gemma-3和Llama-3等模型进行各种方法的实验表明，在低风险下学到的风险规避可以在巨大的风险差异中部分泛化。虽然当前模型表现出改进的风险规避行为，但它们尚未达到足够一致的可靠性，不足以作为防止潜在AI错位的安全措施。 AI

影响通过测试风险规避的泛化能力来研究AI的潜在安全机制，这对于减轻错位风险至关重要。

排序理由学术论文，介绍了一个新的基准测试和实验结果。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，介绍了一个新的基准测试和实验结果。[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: 90 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Kristina Zhang, Junior Chinomso Okoroafor, Benjamin Maltbie, Andrew Lin, Abhitej Bokka, Elliott Thornley · 2026-07-07 04:00

语言模型中风险规避的分布外泛化

arXiv:2607.02755v1 Announce Type: cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but risk-averse AIs would tend to prefer low-risk, low-reward strategies like cooperation over high-risk, hig…

本文如何被排名

报道来源 [1]

语言模型中风险规避的分布外泛化

相关实体

相关话题