1
In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
提出原位反馈方法，让专家在对话中逐轮优化LLM输出，提升多轮协作的可靠性。
arXiv:2510.00777v2 Announce Type: replace Abstract: LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that mod…