LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
Experiments show that the rubric-based rewards reliably distinguish legal responses of different quality and that DPO training on the preference data improves performance across all three dimensions, and Dimension-wise analyses further support the effectiveness of the proposed taxonomy and reward construction.
Yi-Da Cai, Xin Dai, Bing-Xiang He et al.
· 0 citations