Topology-aware Multi-task Learning Framework for Civil Case Judgment Prediction

Y Le, S **ao, Z **ao, K Li - Expert Systems with Applications, 2024‏ - Elsevier
The civil case judgment prediction (CCJP) task involves automatically determining whether
the plea of a plaintiff should be supported by analyzing the given civil case materials …

Heproto: A hierarchical enhancing protonet based on multi-task learning for few-shot named entity recognition

W Chen, L Zhao, P Luo, T Xu, Y Zheng… - Proceedings of the 32nd …, 2023‏ - dl.acm.org
Few-shot Named Entity Recognition (NER) task, which aims to identify and classify entities
from different domains with limited training samples, has long been treated as a basic step …

The Craft of Selective Prediction: Towards Reliable Case Outcome Classification--An Empirical Study on European Court of Human Rights Cases

T Santosh, I Chowdhury, S Xu, M Grabmair - arxiv preprint arxiv …, 2024‏ - arxiv.org
In high-stakes decision-making tasks within legal NLP, such as Case Outcome Classification
(COC), quantifying a model's predictive confidence is crucial. Confidence estimation …

Post-hoc Facts augmented Legal Judgment Prediction

Y An, L Yue, W Gao, K Zhang, Q Liu - International Conference on …, 2024‏ - Springer
Abstract Legal Judgment Prediction (LJP) has emerged as a fundamental aspect of legal AI
systems, encompassing both civil and criminal cases. In this paper, we focus on civil LJP …