Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Trajectory-Augmented Policy Optimization (TAPO) enhances large language model reasoning by creating explicit corrective trajectories that preserve erroneous reasoning while incorpo…
Hugging Face · Daily Papers
·Zhilin Huang, Hang Gao
·
·▲ 13 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Zhilin Huang, Hang Gao, Ziqiang Dong, Yuan Chen, Yifeng Luo, Chujun Qin
- 13 upvotes da comunidade
- Temas: self-distillation, logit-level alignment, KL divergence, trajectory construction, micro-reflective corrections, policy optimization
Resumo
Resumo original (em inglês), extraído do paper:
Trajectory-Augmented Policy Optimization (TAPO) enhances large language model reasoning by creating explicit corrective trajectories that preserve erroneous reasoning while incorporating natural-language diagnoses and corrections, outperforming traditional self-distillation methods through improved error-correction capabilities.
// relacionados
Leia também
Blog
How Businesses Are Building Specialized AI They Can Trust
Blog
Fika Jobs raises $4M to build a video-first hiring platform where AI agents interview candidates
Blog
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
Blog