1
Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees
提出学习-推迟框架，为LLM在抽取式问答中分配查询提供理论保证，实现最优资源权衡。
arXiv:2410.15761v4 Announce Type: replace-cross Abstract: Large Language Models excel in generative tasks but exhibit inefficiencies in structured tex…