paper-with-me

Papers

Evolutionary Strategies lead to Catastrophic Forgetting in LLMs

2026-01-28 · Immanuel Abdi, Akshat Gupta, Micah Mok, Alexander Lu, Nicholas Lee, Gopala Anumanchipalli arxiv

One of the biggest missing capabilities in current AI systems is the ability to learn continuously after deployment. Implementing such continually learning systems have several challenges, one of which is the large memory requirement of gradient-based algorithms that are used to train state-of-the-art LLMs. Evolutionary Strategies (ES) have recently re-emerged as a gradient-free alternative to traditional learning algorithms and have shown encouraging performance on specific tasks in LLMs. In this paper, we perform a comprehensive analysis of ES and specifically evaluate its forgetting curves when training for an increasing number of update steps. We first find that ES is able to reach performance numbers close to GRPO for math and reasoning tasks with a comparable compute budget. However, and most importantly for continual learning, the performance gains in ES is accompanied by significant forgetting of prior abilities, limiting its applicability for training models online. We also explore the reason behind this behavior and show that the updates made using ES are much less sparse and have orders of magnitude larger $\ell_2$ norm compared to corresponding GRPO updates, explaining the contrasting forgetting curves between the two algorithms. With this study, we aim to highlight the issue of forgetting in gradient-free algorithms like ES and hope to inspire future work to mitigate these issues.

📄 PDF Abstract BibTeX arXiv:2601.20861

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models

2025-05-23 · Chi-Yuan Hsiao, Ke-Han Lu, Kai-Wei Chang, Chih-Kai Yang 외

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS an…

Continual LearningQuestion Answering

Revisiting Catastrophic Forgetting in Large Language Model Tuning

2024-06-07 · Hongyu Li, Liang Ding, Meng Fang, DaCheng Tao

Catastrophic Forgetting (CF) means models forgetting previously acquired knowledge when learning new data. It compromises the effectiveness of large language models (LLMs) during fine-tuning, yet the underlying causes ha…

Language ModelingLanguage ModellingLarge Language Modelmodel

Examining Forgetting in Continual Pre-training of Aligned Large Language Models

2024-01-06 · Chen-An Li, Hung-Yi Lee

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developi…

Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study

2025-05-24 · Ziyang Cheng, ZHIXUN LI, Yuhan Li, Yixin Song 외

Nowadays, real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge without forgetting previously learned informati…

Continual Learning

Reducing catastrophic forgetting when evolving neural networks

2019-04-05 · Joseph Early

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately,…

Reinforcement Learning