Paper
LLMs & Texto
Forecasting Future Behavior as a Learning Task
Behavior Forecasters are trained to predict large reasoning model outputs from single trajectories, outperforming large language models while requiring significantly less computati…
Hugging Face · Daily Papers
·Mosh Levy, Yoav Goldberg
·
·▲ 1 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Mosh Levy, Yoav Goldberg, Asa Cooper Stickland
- 1 upvotes da comunidade
- Temas: large reasoning models, behavior forecasting, reasoning trajectories, inference cost, end-to-end fine-tuning, trajectory analysis
Resumo
Resumo original (em inglês), extraído do paper:
Behavior Forecasters are trained to predict large reasoning model outputs from single trajectories, outperforming large language models while requiring significantly less computational cost.Onde ler
// relacionados
