PulseAugur
中
实时 08:37:34
English(EN) Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev

Jev 决策模型在测试中显示出显著的选项集依赖性

作者 PulseAugur 编辑部 · [1 个来源] ·

一篇新发表在 arXiv 上的研究调查了托管决策模型的选项集依赖性，特别是测试了 Jev 模型。研究发现，在分类任务中添加无关选项会显著改变分配给正确和错误选项的概率。这种依赖性在包括 Banking77、CLINC150 和 AG News 在内的各种数据集上都有观察到，并且随着选项数量的增加，这种变化是方向性的并呈递增趋势。研究表明，Jev 的概率应根据给定查询中使用的特定选项列表来解释。 AI

影响 强调了托管决策模型中潜在的偏见，建议根据选项集仔细解释概率输出。

排序理由 该集群包含一篇详细介绍特定 AI 模型行为的实验结果的研究论文。[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 →

Jev 决策模型在测试中显示出显著的选项集依赖性

本文如何被排名

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍特定 AI 模型行为的实验结果的研究论文。[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]

  1. arXiv cs.AI TIER_1 English(EN) · Dushyant Rajput (AltSlate Labs LLP), Nirdesh Chauhan (AltSlate Labs LLP), Siddharth Kosaraju (AltSlate Labs LLP) ·

    托管式决策模型是否会考虑无关选项？一项预先注册的关于Jev中选项集依赖性的测试

    arXiv:2610.16655v1 Announce Type: new Abstract: Decision APIs that return a probability for each option are routinely used as if those probabilities were properties of the options themselves. That reading is valid only if the model satisfies independence of irrelevant alternative…

相关实体

相关话题