1
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
语义流正则化破解LLM生成两难：在保持连贯性前提下大幅提升多样性，为长文本生成注入新活力。
arXiv:2605.27971v1 Announce Type: cross Abstract: When large language models are fine-tuned to generate persona- or tone-conditioned responses, their …