2605.30148v1 May 28, 2026 cs.LG

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies

Risto Miikkulainen
Risto Miikkulainen
Citations: 88
h-index: 5
Xin Qiu
Xin Qiu
Citations: 51
h-index: 4
Kajetan Schweighofer
Kajetan Schweighofer
Citations: 205
h-index: 7
Conor F. Hayes
Conor F. Hayes
Citations: 52
h-index: 4
Roberto Dailey
Roberto Dailey
Citations: 5
h-index: 1

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 forgetting (1) is better characterized as performance drift rather than irreversible forgetting, with prior-task performance often recovering during ES training; and (2) is not a specific failure mode of ES, but can also arise for fine-tuning with RL methods. Second, it analyzes when and why such drift arises, highlighting its dependence on ES training dynamics, particularly random walk behavior in weakly constrained directions of the weight space. Third, based on these insights, it introduces Anchored Weight Decay (AWD) as a parameter-space regularization technique that constrains optimization toward the initial model parameters. AWD effectively stabilizes prior-task performance while preserving target-task performance, achieving benefits comparable to large ES population sizes at much lower computational cost. Thus, contrary to previous beliefs, the paper shows that prior-task forgetting under ES is largely avoidable, positioning ES as a promising approach for continual learning in LLMs.

0 Citations
0 Influential
3.5 Altmetric
17.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!