yourbench-testing/coding-questions-test

该数据集名为编程问题测试，是使用YourBench开源框架从文档集合生成的领域特定基准测试。数据集包含三个配置：1) chunked：将文本分割成基于令牌的单跳和多跳块；2) ingested：读取原始源文档并转换为标准化markdown；3) single_shot_questions：为每个文本块生成独立的问答对。数据集生成流程包括文档摄取、分块处理和问题生成三个主要步骤，旨在为编程领域创建测试问题集。

This dataset, named Coding Questions Test, was generated using the YourBench open-source framework to create domain-specific benchmarks from document collections. It contains three configurations: 1) chunked: splits texts into token-based single-hop and multi-hop chunks; 2) ingested: reads raw source documents and converts them to normalized markdown; 3) single_shot_questions: generates standalone question-answer pairs per chunk. The dataset generation pipeline involves three main steps: document ingestion, chunking processing, and question generation, aiming to create test question sets for the programming domain.