LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

LLM-as-a-Tutor framework extends LLM role from judge to tutor by dynamically adjusting prompt difficulty through pairwise comparison and constraint addition, improving instruction-…

Hugging Face · Daily Papers ·Yujin Kim, Namgyu Ho · ·▲ 22 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Yujin Kim, Namgyu Ho, Sangmin Hwang, Joonkee Kim, Yongjin Yang, Sangmin Bae

  • 22 upvotes da comunidade
  • Temas: reinforcement learning, large language models, instruction following, reward signals, policy adaptation, prompt adaptation

Resumo

Resumo original (em inglês), extraído do paper:

LLM-as-a-Tutor framework extends LLM role from judge to tutor by dynamically adjusting prompt difficulty through pairwise comparison and constraint addition, improving instruction-following performance in reinforcement learning.

Onde ler

compartilhar: