SecureFinAI-Lab/Regulations_definition

该数据集是为了评估大型语言模型在理解和生成金融监管合规语境中常用术语定义的能力而设计的。它包括经过精心挑选的关键术语及其在监管文件中的定义。数据集涵盖了欧洲OTC衍生品市场、美国证券市场、美国银行系统以及会计审计标准等不同领域。它包含了美联储规定、EMIR、会计审计标准等类别的100、50、30个条目。使用BERTScore作为评估模型生成定义质量的指标。

This dataset is designed to evaluate the capability of large language models to understand and generate definitions for terms commonly used in financial regulatory and compliance contexts. It includes a curated collection of key terms and their definitions as used in regulatory documents across different domains such as the European OTC derivative market, the U.S. securities market, the U.S. banking system, and accounting and auditing standards. It contains 100, 50, and 30 items from categories like Federal Reserve Regulations, EMIR, and Accounting and Auditing, respectively. BERTScore is used as a metric to assess the quality of the definitions generated by the model.