English(EN) Precedent Labels and Facts Shift LLM Approval Decisions in Opposite Directions

大型语言模型的审批决策受先例标签影响，而非事实

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

一篇新研究论文探讨了大型语言模型（LLMs）在面对过往案例示例时如何做出决策。研究发现，像DeepSeek V4.1 Flash、GPT-5.6 Luna和Claude Haiku 5.5这样的大型语言模型，会显著受到过往案例记录决策的影响，先例从拒绝转向批准会使批准率提高30-55%。相反，过往案例的事实内容似乎会降低批准率，这表明当与有利事实并列时，大型语言模型可能认为当前请求较弱。这种效应在各种政策和模型中都有观察到，突显了在由大型语言模型驱动的决策系统中，分别评估先例数据的factual和决策组成部分的重要性。 AI

影响强调了大型语言模型决策中可能存在的偏见，这些偏见取决于先例数据的呈现方式，并影响客户服务和法律分析等领域的应用。

排序理由研究论文，详细介绍大型语言模型的决策过程。[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: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍大型语言模型的决策过程。[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, model release; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Junwei Yao, Zike Yang, Yongxi Zhou, Yanxian Chen, Jianan Liu, Jiaxi Wen, Zhijun Wang · 2026-11-04 05:00

先例标签和事实使LLM批准决策朝相反方向移动

arXiv:2611.00672v1 Announce Type: new Abstract: When a language model decides refund or claim requests under written policies, the system can show it similar past cases. Each past case has two parts: its facts and the decision recorded for it. We separate the two. A model sees a …

本文如何被排名

报道来源 [1]

先例标签和事实使LLM批准决策朝相反方向移动

相关实体

相关话题