Multi-LexSum:多粒度民权诉讼的真实世界摘要
Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities
摘要:
随着大语言模型的出现,用于抽象摘要的方法已经取得了很大的进步,为在应用中使用以帮助知识工作者处理笨重的文档集合创造了潜力。其中一个这样的设置是民权诉讼信息交换所(CRLC)(https:clearinghouse.net),它发布有关大规模民权诉讼的信息,服务律师,学者和公众。如今,CRLC中的摘要需要对律师和法律专业学生进行广泛的培训,他们在每个案件中花费数小时来理解多个相关文件,以便对关键事件和结果进行高质量的摘要。出于这种持续的真实世界总结工作的动机,我们引入了Multi-LexSum,这是一个从正在进行的CRLC写作中提取的9,280个专家撰写的摘要的集合。Multi-LexSum提出了一个具有挑战性的多文档摘要任务,因为源文档的长度通常超过200页。此外,Multi-LexSum与其他数据集的不同之处在于其多个目标摘要,每个目标摘要都有不同的粒度(从一句话的“极端”摘要到超过500字的多段叙述)。我们提出了广泛的分析表明,尽管在训练数据的高质量的摘要(坚持严格的内容和风格的指导方针),国家的最先进的摘要模型在这项任务上表现不佳。我们在https://multilexsum.github.io上发布Multi-LexSum,以进一步研究摘要方法,并促进应用程序的开发,以协助CRLC的使命。
英文摘要:
With the advent of large language models, methods for abstractive summarization have made great strides, creating potential for use in applications to aid knowledge workers processing unwieldy document collections. One such setting is the Civil Rights Litigation Clearinghouse (CRLC) (https://clearinghouse.net),which posts information about large-scale civil rights lawsuits, serving lawyers, scholars, and the general public. Today, summarization in the CRLC requires extensive training of lawyers and law students who spend hours per case understanding multiple relevant documents in order to produce high-quality summaries of key events and outcomes. Motivated by this ongoing real-world summarization effort, we introduce Multi-LexSum, a collection of 9,280 expert-authored summaries drawn from ongoing CRLC writing. Multi-LexSum presents a challenging multi-document summarization task given the length of the source documents, often exceeding two hundred pages per case. Furthermore, Multi-LexSum is distinct from other datasets in its multiple target summaries, each at a different granularity (ranging from one-sentence "extreme" summaries to multi-paragraph narrations of over five hundred words). We present extensive analysis demonstrating that despite the high-quality summaries in the training data (adhering to strict content and style guidelines), state-of-the-art summarization models perform poorly on this task. We release Multi-LexSum for further research in summarization methods as well as to facilitate development of applications to assist in the CRLC's mission at https://multilexsum.github.io.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。