Datasets:
ArXiv:
License:
| license: mit | |
| <h1 align="center">LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models</h1> | |
| # News | |
| - Our preprint [LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models](https://arxiv.org/abs/2609.39071) has released. | |
| # Introduction | |
| High-quality legal responses require more than a correct final answer. They should use precise and objective language, identify relevant legal subjects and facts, apply appropriate statutes, and present complete and coherent reasoning. Coarse-grained holistic rewards can obscure these distinct requirements. | |
| **LexReward** is a taxonomy-driven reward framework that decomposes legal response quality into three complementary dimensions: | |
| | Dimension | Evaluation criteria | | |
| | :--- | :--- | | |
| | **Style** | Word specificity, subjective-word control, sentence coherence, sentence structure, and collocation correctness. | | |
| | **Element** | Legal subjects, case facts, statutory grounds, and judicial decisions. | | |
| | **Chain** | Reasoning order, completeness, correctness, and non-redundancy. | | |
| The framework operationalizes these criteria with interpretable rule-based evaluators and LLM judges. Rubric scores guide preference construction from diverse model-generated responses. We then train **LexRM**, a family of dimension-specific reward models, with a Bradley-Terry pairwise objective. | |
| The paper evaluates rubric rewards and LexRM through preference selection and test-time scaling, and studies downstream policy optimization with DPO and GRPO. Its experiments show that rubric-guided preference data and learned reward models improve legal response quality across the three dimensions. | |
| # Dataset Statistics | |
| The following statistics describe the **paper's experiments**, not dataset files distributed in this code package. | |
| | Dimension | Source data | Training or construction data | Evaluation data | | |
| | :--- | :--- | :--- | :--- | | |
| | Style | CLASE | 4,000 training queries used for preference construction | 1,000 official test instances | | |
| | Element | JEC-QA and LexChain | 2,736 source instances yielding 2,244 preference pairs | 3,000 LegalDelta in-domain test instances | | |
| | Chain | LexChain | 9,550 training instances, including 4,000 queries allocated to preference training | 1,000 official test instances | | |
| # Dataset Format | |
| Both constructors output chat-format RM preference pairs: | |
| ```json | |
| { | |
| "chosen": [ | |
| {"role": "user", "content": "Case facts and task instructions..."}, | |
| {"role": "assistant", "content": "Preferred model-generated response..."} | |
| ], | |
| "rejected": [ | |
| {"role": "user", "content": "Case facts and task instructions..."}, | |
| {"role": "assistant", "content": "Dispreferred model-generated response..."} | |
| ], | |
| "meta": { | |
| "source_row_id": 0, | |
| "pair_group": "A", | |
| "tier_ratio": "5:3:2", | |
| "chosen_index": 0, | |
| "rejected_index": 1, | |
| "chosen_score": -0.2, | |
| "rejected_score": -0.8 | |
| } | |
| } | |
| ``` | |
| ## Field Descriptions | |
| | Field | Description | | |
| | :--- | :--- | | |
| | `chosen` | Chat messages containing the prompt and preferred generated response. | | |
| | `rejected` | Chat messages containing the same prompt and dispreferred generated response. | | |
| | `meta.source_row_id` | Identifier of the source query in the candidate pool. | | |
| | `meta.pair_group` / `meta.tier` | Pair category A, B, or C. CLASE uses `pair_group`; LexChain uses `tier`. | | |
| | `meta.tier_ratio` | Construction ratio, `5:3:2`. | | |
| | `meta.chosen_index` / `meta.rejected_index` | Selected candidate indices in the original five-response pool. | | |
| | Scores | CLASE records selected scores in `meta`; LexChain also provides top-level `chosen_score` and `rejected_score`. Higher scores are preferred. | | |
| LexChain outputs additionally preserve `chosen_model`, `rejected_model`, all five scores in `meta.row_scores`, and `meta.judge_model`. Both training scripts consume the shared `chosen` and `rejected` fields. | |
| # Dataset Example | |
| The following pair is synthetic and shown in English for readability. The experiments use Chinese legal text. | |
| ```json | |
| { | |
| "chosen": [ | |
| { | |
| "role": "user", | |
| "content": "Rewrite the following case summary as a formal judicial explanation without adding facts: the loan is due and remains unpaid." | |
| }, | |
| { | |
| "role": "assistant", | |
| "content": "The loan has matured, and the borrower has not fulfilled the repayment obligation. The outstanding loan therefore remains payable." | |
| } | |
| ], | |
| "rejected": [ | |
| { | |
| "role": "user", | |
| "content": "Rewrite the following case summary as a formal judicial explanation without adding facts: the loan is due and remains unpaid." | |
| }, | |
| { | |
| "role": "assistant", | |
| "content": "The money is due and they have not paid it back, so they still need to pay." | |
| } | |
| ], | |
| "meta": { | |
| "source_row_id": 0, | |
| "pair_group": "A", | |
| "tier_ratio": "5:3:2", | |
| "chosen_index": 0, | |
| "rejected_index": 1, | |
| "chosen_score": -0.2, | |
| "rejected_score": -0.8 | |
| } | |
| } | |
| ``` | |
| ## Citation | |
| If you use this work, please cite our [arXiv preprint](https://arxiv.org/abs/2609.39071): | |
| ```bibtex | |
| @article{cai2026lexreward, | |
| title = {{LexReward}: A Taxonomy-Driven Reward Framework for Legal Language Models}, | |
| author = {Yida Cai and Xin Dai and Bingxiang He and Huiyuan Xie and Yuxiao Ye and Zhenghao Liu and Yang Bai and Zhiyuan Liu}, | |
| year = {2026}, | |
| journal = {arXiv preprint arXiv:2609.39071} | |
| } | |
| ``` | |