Optimizing Diversity and Quality through Base-Aligned Model Collaboration 事件

Optimizing Diversity and Quality through Base-Aligned Model Collaboration arXiv:2511.05650v2 Announce Type: replace Abstract: Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations, especially in open-ended generation tasks. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level model collaboration framework that dynamically combines a base LLM with its aligned counterpar