热点
"训练目标" 相关文章
深度｜Anthropic团队重磅发现：模型会假装迎合人类，以维护初始偏好
Z Potentials 2025-01-09T17:00:16.000000Z
Bidirectional Causal Language Model Optimization to Make GPT and Llama Robust Against the Reversal Curse
MarkTechPost@AI 2024-11-16T04:50:08.000000Z