cs.CLNov 11, 2026

Towards Better Legal Reasoning LLMs: Signal Balancing and Reward Scheduling

Authors: Yinghao Hu, Qian Xiao, Yuting Huang, Kaisong Song, Yiquan Wu, Ang Li, Junjie Cao, Jun Lin, 

Organizations: Zhejiang University, Hangzhou, China · Alibaba Group, Hangzhou, China · Northeastern University, Shenyang, China · University of Macau, Macao, China

Abstract

In the legal domain, LLMs can improve reliability and interpretability by generating explicit reasoning traces. However, training LLMs to produce high-quality reasoning traces remains challenging. Existing supervised fine-tuning methods struggle when reasoning traces are significantly longer than final answers, as the learning signal for the answer becomes diluted. Meanwhile, reinforcement learning methods such as Group Relative Policy Optimization also have several limitations, including costly reward design, performance plateaus, and reward hacking. We therefore propose a two-stage training framework. In Stage I, JurisCoT-SFT employs a length-normalized dual objective to balance learning signals between reasoning traces and final answers. In Stage II, Lifecycle-Aware Backtrackable Policy Optimization dynamically evaluates and retires auxiliary reward signals based on their impact on final evaluation objectives, enabling efficient reward utilization. Our framework substantially improves legal reasoning performance on relevant tasks selected from multiple legal benchmarks, including ChJGBench, LawBench, and LegalBench. Experimental results demonstrate consistent improvements in both reasoning trace quality and final answer accuracy, while our models remain competitive with larger models.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models

    Apr 26, 2026Tianchun Li, Haochen Liu, Vishwa Pardeshi +5Synthetic Data GenerationSmall Language Models

  2. Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models

    Nov 11, 2025Wenhan Yu, Xinbo Lin, Lanxin Ni +2Legal ReasoningStructured Reasoning in Language Models

  3. LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning

    Sep 22, 2026Qingjing Chen, Junkai Zhang, Shaochun Wang +7LLM Reasoning with GraphsGraph Retrieval-Augmented Generation