yale-nlp/LitSearch-NLP-Class

LitSearch是一个针对科学文献搜索的检索基准，包含597个关于最近机器学习和自然语言处理论文的现实查询集合以及一个包含6809个文档的检索语料库。每个查询都有golden paper IDs、specificity和quality注释，以及关于查询来源的元数据。检索语料库包括提取的标题、摘要和出向引用论文ID。

LitSearch is a retrieval benchmark for scientific literature search, containing a set of 597 realistic queries about recent machine learning and natural language processing papers, as well as a retrieval corpus of 6809 documents. Each query is accompanied by golden paper IDs, specificity and quality annotations, and metadata about the source of the query. The retrieval corpus includes extracted titles, abstracts, and outgoing citation paper IDs.