McGill-NLP/CHASE-Code

CHASE（用合成评估挑战AI）是一个统一框架，用于合成生成无需人工参与的大型语言模型（LLM）挑战性问题。该框架将生成过程分解为独立的子任务，确保了生成问题的高质量和正确性。CHASE被应用于三个不同领域：基于文档的问答、仓库级别的代码补全和数学推理。

CHASE (Challenging AI with Synthetic Evaluations) is a unified framework for synthetically generating challenging problems for Large Language Models (LLMs) without human involvement. The framework decomposes the generation process into independently verifiable sub-tasks, ensuring high quality and correctness of the generated problems. CHASE is applied across three diverse domains: document-based question answering, repository-level code completion, and math reasoning.