Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies 事件

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies arXiv:2605.30148v1 Announce Type: cross Abstract: Evolution Strategies (ES) has recently emerged as a competitive alternative to reinforcement learning (RL) for large language model (LLM) fine-tuning, offering advantages through simplicity, scalability, and inference-only training. However, recent work suggests that ES fine-tuning on new tasks may induce forgetting of prior tasks. First, this paper shows that prior task forgetti