Verifier-free reinforcement learning with probability-based rewards offers a promising way to train LLMs on general reasoning tasks where external verifiers are unavailable. Yet the reliability of these rewards, especially in long-horizon reasoning, remains underexplored. This work identifies a length-dependent failure...
Shiu-hong Kao, Yu-Bo Zhao, Zhen Tian et al.· 0 citations
When evaluated on unseen species, the best adapted VLMs outperformed specialist models trained on the same data in identifying merge errors and LoRA on a few thousand labels brought open models level with specialist models.
Yi-Cong Li, Jun-Jie Wang, Leander Lauenburg et al.· 0 citations
It is shown that the minimum aggregation is essential: mean aggregation can be exploited, saturating the proxy reward while degrading accuracy, and the minimum aggregation is essential for PROSE, Process Reward Guided Self-Training.
Kai-Long Fan, An-Qi Pu, Yi-Chen Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.