English(EN) Adversarial Cues in Decision Models Used as Judges: The Role of Request Presentation

请求呈现方式显著改变AI裁判在DROP和GSM8K数据集上的表现

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员发现，裁判请求的呈现方式会显著影响决策模型的性能，导致错误接受率增加。具体而言，在候选者的请求呈现中添加冒号会导致在DROP和GSM8K数据集上错误接受率大幅上升。虽然GPT-6 Sol没有表现出这种脆弱性，但该研究强调了请求格式中看似微小的变化如何影响模型准确评估响应的能力。 AI

影响强调了提示工程中细微的变化如何导致AI评估模型性能显著下降。

排序理由该集群包含一篇在arXiv上发表的研究论文，详细介绍了AI模型行为的发现。[lever_c_demoted from research: ic=1 ai=1.0]

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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇在arXiv上发表的研究论文，详细介绍了AI模型行为的发现。[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: 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。

arXiv cs.CL TIER_1 English(EN) · Hongliang Liu · 2026-10-09 04:00

决策模型中用作裁判的对抗性线索：请求呈现的作用

arXiv:2610.11436v1 Announce Type: new Abstract: An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earlier value matches the reference. We show that adding one colon to a candidate can violate this requirement depen…