promptquine-evolving-in-context-prompts

【数据与研究】Automatically discovers optimal in-context learning prompts through evolutionary token pruning that removes redundant demonstrations to create effective 'gibberish' prompts. Matches state-of-the-art optimization with low-data regimes. Use for automated prompt discovery without manual tuning or human expertise.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准