References Improve LLM Alignment in Non-Verifiable Domains
arXiv:2602.16802v1 Announce Type: new Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to …
Kejian Shi, Yixin Liu, Peifeng Wang, Alexander R. Fabbri, Shafiq Joty, Arman Cohan
4 views
