works on
humanities and social sciences 1large language models 1preference alignment 1quality evaluation 1synthetic data generation 1

From the 1 of 10 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

Zhanming Shen, Jintao Tong, Shaotian Yan +9

On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-lev…