Go to ACL ARR 2025 May homepageUnilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference
Abstract: Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remains underexplored. In this paper, we introduce Unilaw-R1, a large language model tailored for legal reasoning. With a lightweight 7-billion parameter scale, Unilaw-R1 significantly reduces deployment cost while effectively tackling three core challenges in the legal domain: insufficient legal knowledge, unreliable reasoning logic, and weak business generalization. To enhance its reasoning capability, we first construct Unilaw-R1-Data, a high-quality dataset containing $\sim$17K distilled and screened chain-of-thought (CoT) samples. Based on this, we adopt a two-stage training strategy combining Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), which significantly boosts the model’s performance on complex legal reasoning tasks and supports interpretable decision-making in legal AI applications. To assess legal reasoning ability, we also introduce Unilaw-R1-Eval, a dedicated benchmark designed to evaluate models across single- and multi-choice legal tasks. Unilaw-R1 demonstrates strong results on authoritative benchmarks, outperforming all models of similar scale and achieving performance on par with the much larger DeepSeek-R1-Distill-Qwen-32B (54.9). Following domain-specific training, it also showed significant gains on LawBench and LexEval, exceeding Qwen-2.5-7B-Instruct (46.6) by an average margin of 6.6 points.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: Legal Large Language Model, Reinforcement Learning, Iterative Inference
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources, Data analysis
Languages Studied: Chinese, English
Submission Number: 1009
Loading