LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
- 类型：arxiv
- 标识：2609.39071
- 链接：https://arxiv.org/abs/2609.39071
- 主分类：evaluation
- 形态：method
- TLDR：Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing reward methods, however, often rely on coarse-grained holistic judgments, providing limited domain specificity and interpretability. We introduce LexReward, a taxonomy-driven framework for legal reward modeling. LexReward characterizes legal response quality along three complementary dimensions: Style, covering lexical and syntactic quality; Element, assessing legal subjects, facts, statutes, and decisions; and Chain, evaluating the order, com
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-10-05-agent-rag-longcontext-candidates.json