牛哥精选 · 半年

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv AI 2026-07-02

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

大模型自解释的可信度会随规模变化？75个模型横评揭示反事实一致性规律，看懂LLM解释的可靠性边界

arXiv:2503.13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausibl…

llm 可解释性反事实评估模型规模自解释

🤖 AI·大模型 arXiv AI 2026-06-04

CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems

专为细粒度反事实评估打造的合成人脸数据集，系统测评人脸识别系统的鲁棒性新基准！

arXiv:2407.13922v3 Announce Type: replace-cross Abstract: Face recognition (FR) systems are widely deployed in critical applications, making their rel…

人脸识别合成数据集反事实评估计算机视觉鲁棒性测试

🤖 AI·大模型 arXiv AI 2026-06-01

Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents

反事实评估直击临床大模型盲区，暴露出传统测试无法察觉的能力不均衡，为AI安全应用画红线

arXiv:2605.30590v1 Announce Type: cross Abstract: Two clinical AI systems can score nearly identically on coverage-based rubrics yet behave radically …

反事实评估临床大模型 ai评测能力剖面人工智能安全

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems

Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents

📅 日期