#phi-3.5-mini

Phi-3.5-Mini: 1 AI articles covering phi-3.5-mini news, analysis, and research

Articles

Do Small Language Models Know What They Don't Know? New ResearchNEW⭐9

📅 2小时前👁 4 views

New research shows token entropy fails as a confidence signal in sub-3B language models, while semantic entropy enables routing gains up to +50 percentage point...