Skip to content
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

Timeline

Follow the coverage from different angles.

Oct 8, 2026
  1. arXiv · Machine Learning Theory
    Conditional 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 –

02.557.510Oct8Oct8Oct8Oct8

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.