HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation.
Feng Xiong, Hongling Xu, Yifei Wang, Runxi Cheng, Yong Wang, Xiangxiang Chu
Browse the full EMNLP paper archive.
Feng Xiong, Hongling Xu, Yifei Wang, Runxi Cheng, Yong Wang, Xiangxiang Chu
Browse the full EMNLP paper archive.