Reinforcement Learning with Argument-Structured Reward for Court Decision Abstractive Summarization
Year: 2025
Type: book-chapter
Abstract: Court decision summarization is challenging due to the significant length and structural complexity of legal documents, which makes existing reinforcement learning (RL)-based abstractive summarization methods less effective. We propose an RL-based abstractive legal summarization model with a novel argument-structured reward mechanism. It leverages Issue–Reason–Conclusion components to compute fine-grained sub-rewards and aggregate them into a final reward. This design provides more reliable learning signals for model optimization. Experiments on the Indian Supreme Court dataset with Longformer-Encoder-Decoder (LED) and Llama demonstrate consistent improvements over non-argument-structured methods. To the best of our knowledge, this is the first work to incorporate argumentative structures into RL-based summarization, offering a novel direction for improving legal summarization.
DOI: 10.3233/faia251603
Authors: Yuntao Kong, Ye Xiong, Shuyuan Zheng, Ken Satoh
Language: English
Subfield: Law
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4416988064