1
Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
多轮对话中，长距离依赖与信息稀疏是老大难，这篇论文提出的Self-Recall Thinking框架，让模型在推理时主动召回历史关键轮次，无需外部模块，4.7% F1提升+14.7%延迟缩减，平衡了准确与效率，思路清奇。
arXiv:2605.15102v1 Announce Type: cross Abstract: Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies ac…