1
CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes
首个评估数据精炼配方组合与顺序敏感执行的基准,直击大模型数据处理链条的可靠性盲区
arXiv:2606.31435v1 Announce Type: new Abstract: Data refinement involves executing multi-step recipes over evolving text states, where both compositio…