AUEB-NLP/lar-echr

LAR-ECHR是一个用于评估大型语言模型在法律论证推理能力的新型任务的数据集。该数据集基于欧洲人权法院的案件，要求在给定的案件事实下，从多个选择题选项中选择正确的后续陈述。数据集包含案件ID、案件编号、完整事实段落列表、事实摘要、前三个论证的文本、每个选项对应的论证文本以及正确选择的标签。数据集分为训练集、验证集和测试集，分别包含5、98和300个样本。

LAR-ECHR is a dataset for a novel task designed to evaluate the legal reasoning capabilities of Large Language Models (LLMs). It is based on cases from the European Court of Human Rights (ECHR) and requires selecting the correct next statement (from multiple choice options) in a chain of legal arguments from court proceedings, given the facts of the case. The dataset includes case ID, case number, a list of paragraphs of complete facts, a summary of the facts, the text of the previous three arguments, the text of the argument corresponding to each option, and the label of the correct choice. The dataset is split into training, validation, and test sets with 5, 98, and 300 samples respectively.