llm-self-correction-confidence-signals 86/100

大型语言模型通过内部置信度信号检测和纠正自身错误的研究。基于决策神经科学二阶置信度模型和PANL token机制。

no risky patterns detected

Type: Agent skill (SKILL.md) · Category: LLM & Model APIs · Source: https://github.com/hiyenwong/ai_collection/tree/HEAD/collection/skills/ai-ml/llm

Score breakdown

Why this score

• Docs include setup/install commands (one-time setup, not penalised)
• Instructions only: no bundled scripts
• Last updated 0 days ago +15
• 3 GitHub stars +1
• 12 contributors +5
• Description and source link present +15

Always review files before installing. How scores work. Request a correction