English(EN) BMMS: Policy-Conditioned Measurement of Behavioral Compliance in Language Models

新的BMMS指标显示GPT-4o未能达到OpenAI的模型规范

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 05:00

一篇新研究论文介绍的行为失调度量套件（BMMS）旨在根据特定策略合规性而非一般行为维度来评估语言模型。该套件包括合规性达成得分（CAS）和合规性鲁棒性裕度（CRM）等指标，以评估模型在多大程度上遵守既定规则。在测试中，GPT-4o在OpenAI的模型规范上表现出显著的失败率（70.7%），而Claude模型则显示出低得多的失败率。 AI

影响引入了一个评估LLM策略合规性的新框架，可能影响受监管行业评估AI安全的方式。

排序理由介绍语言模型新评估方法的 ist 研究论文。 [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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍语言模型新评估方法的 ist 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, 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。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Anthony Rhodes, Gadi Singer · 2026-11-09 05:00

BMMS：语言模型行为合规性的策略条件测量

arXiv:2611.09147v1 Announce Type: cross Abstract: Behavioral evaluation of language models fixes its dimensions in advance: hallucination, sycophancy, toxicity, over-refusal. An operator in a regulated industry needs a different question answered: does a system do what a particul…

本文如何被排名

报道来源 [1]

BMMS：语言模型行为合规性的策略条件测量

相关实体

相关话题