Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
Paper LLMs & Texto

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Epi2Diff framework transforms LRM reasoning traces into cognitive episodes to predict human item difficulty more accurately than existing methods.

Hugging Face · Daily Papers ·Chenguang Wang, Ming Li · ·▲ 2 upvotes

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

Autores: Chenguang Wang, Ming Li, Xinyue Zeng, Zhuochun Li, Hong Jiao, Tianyi Zhou

  • 2 upvotes da comunidade
  • Temas: Large Reasoning Models, reasoning traces, cognitive episodes, episode sequences, difficulty prediction, semantic item representations

Resumo

Resumo original (em inglês), extraído do paper:

Epi2Diff framework transforms LRM reasoning traces into cognitive episodes to predict human item difficulty more accurately than existing methods.

Onde ler

compartilhar: