Esteban Garces Arias

Hyperfitting's surprising generation improvements aren't just temperature scaling – they stem from a "Terminal Expansion" in the final transformer block that dynamically reorders token ranks.

Forget temperature tuning: Min-$k$ sampling finds the "semantic cliff" in your LLM's logits, delivering robust and high-quality text even when other methods fall apart.

Language model text is detectable because it misses the "long tail" of human word choice, not because it's less intelligent.