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 2026-06-23

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

用几何方法诊断大模型对齐脆弱性，揭示少量微调即可抹除安全拒答的隐患

arXiv:2606.22676v1 Announce Type: new Abstract: Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be eras…

大模型对齐脆弱性几何诊断安全微调拒绝行为

📝 深度技术 arXiv 机器学习 2026-05-20

Alignment Dynamics in LLM Fine-Tuning

揭秘LLM微调中对齐为何脆弱：从参数动态到输出分布的统一视角

arXiv:2605.18309v1 Announce Type: new Abstract: Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and rein…

llm fine-tunin alignment 机器学习深度学习

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

Alignment Dynamics in LLM Fine-Tuning

📅 日期