LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts
Abstract
Legal Judgment Prediction (LJP) seeks to predict case outcomes given available case information, offering practical value for both legal professionals and laypersons. However, a key limitation of existing LJP models is their limited adaptability to statutory revisions. Current SOTA models are neither designed nor evaluated for statutory revisions. To bridge this gap, we introduce LawShift, a benchmark dataset for evaluating LJP under statutory revisions. Covering 31 fine-grained change types, LawShift enables systematic assessment of SOTA models' ability to handle legal changes. We evaluate five representative SOTA models on LawShift, uncovering significant limitations in their response to legal updates. Our findings show that model architecture plays a critical role in adaptability, offering actionable insights and guiding future research on LJP in dynamic legal contexts.
Cite
Text
Han et al. "LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts." Advances in Neural Information Processing Systems, 2025.Markdown
[Han et al. "LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/han2025neurips-lawshift/)BibTeX
@inproceedings{han2025neurips-lawshift,
title = {{LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts}},
author = {Han, Zhuo and Yang, Yi and Feng, Yi and Huang, Wanhong and Ding, Xuxing and Li, Chuanyi and Ge, Jidong and Ng, Vincent},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/han2025neurips-lawshift/}
}