作者位次 #4/9ACL 2026Poster· Natural Language Processing
R ubric H ub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation
Sunzhu Li · Jiale Zhao · Huimin Ren · Zhenlin Wei · Yang Zhou · Jingwen Yang · Shunyu Liu · Kaike Zhang · Chen Wei
摘要
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verific...