Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
This work provides a new fine-tuning direction for LLMs that could benefit AI deployment by offering more efficient and stable alternatives to RL, though it is incremental in scaling an existing method.
The authors tackled the problem of fine-tuning large language models (LLMs) by scaling up evolution strategies (ES) to billions of parameters, showing that ES outperforms reinforcement learning (RL) methods in sample efficiency, robustness, and stability across multiple tasks.
Fine-tuning pre-trained large language models (LLMs) for down-stream tasks is a critical step in the AI deployment pipeline. Reinforcement learning (RL) is arguably the most prominent fine-tuning method, contributing to the birth of many state-of-the-art LLMs. In contrast, evolution strategies (ES), which once showed comparable performance to RL on models with a few million parameters, was neglected due to the pessimistic perception of its scalability to larger models. In this work, we report the first successful attempt to scale up ES for fine-tuning the full parameters of LLMs, showing the surprising fact that ES can search efficiently over billions of parameters and outperform existing RL fine-tuning methods in multiple respects, including sample efficiency, tolerance to long-horizon rewards, robustness to different base LLMs, less tendency to reward hacking, and more stable performance across runs. It therefore serves as a basis to unlock a new direction in LLM fine-tuning beyond what current RL techniques provide. The source codes are provided at: https://github.com/VsonicV/es-fine-tuning-paper.