Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Paper • 2502.03032 • Published 4 days ago • 49
The Differences Between Direct Alignment Algorithms are a Blur Paper • 2502.01237 • Published 6 days ago • 108
Cultura-Ru-Edu Collection Our dataset for enhancing LLM training with educational content in the Russian language. • 2 items • Updated Nov 26, 2024 • 5
Cultura-Ru-Edu Collection Our dataset for enhancing LLM training with educational content in the Russian language. • 2 items • Updated Nov 26, 2024 • 5