MatrixReward: Reward from Rubric Matrix for Open-Ended Generation
Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism. Pointwise scoring rubrics provide limited information about the relative quality of sample answers under the same prompt; merging multiple rubric judgments into a single score may also mask the differences between thes...
Zi-Hang Shen, Qi Liu, Zi-Xuan Yang et al.
· 0 citations