DeepRetrieval/datasets

DeepRetrieval是一种创新的强化学习方法，用于训练大型语言模型进行无需监督数据查询生成。该方法通过直接尝试和错误，使用检索指标作为奖励，优化查询生成，以达到在各种检索任务中的卓越表现。

DeepRetrieval is an innovative reinforcement learning approach for training Large Language Models to generate queries without supervised data. It optimizes query generation through direct trial and error using retrieval metrics as rewards, achieving state-of-the-art performance across diverse retrieval tasks.