Hot eventLive
提出条件准确率画像CAP诊断LLM评委
1 reports1 sources3 hr ago updated
Get the story
AI overview
2026年10月8日,arXiv Machine Learning Theory 发表一项研究,提出 Conditional Accuracy Profiling(CAP),一种事后诊断框架,用于在不同部署条件下诊断 LLM 评判器。该框架将成对 LLM 评判器的准确率分解为内容敏感性、鲁棒性与理由质量三大类,共八个条件,以刻画评判器在各类条件下的表现差异。目前报道仅介绍框架提出与分类结构,尚无后续验证或应用进展。
Generated from reports · updated 3 hr ago
LatestOct 8
研究提出CAP框架,将LLM评判器准确率分解为三大类八个条件。Timeline
Follow the coverage from different angles.
Oct 8, 2026
- arXiv · Machine Learning TheoryConditional Accuracy Profiles:在不同部署条件下诊断 LLM 评判器
研究提出 Conditional Accuracy Profiling(CAP),一种事后诊断框架,将成对 LLM 评判器的准确率分解为内容敏感性、鲁棒性与理由质量三大类共八个条件。
Heat trend
Current heat 9·Comparable peak 10(Oct 8)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.