MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning

TL;DR

This paper introduces MAML-en-LLM, a meta-training method for large language models that enhances their ability to generalize and adapt to unseen tasks, outperforming existing approaches in various settings.

Contribution

The paper proposes MAML-en-LLM, a novel meta-training approach that produces more generalizable LLM parameters capable of better adaptation to new tasks.

Findings

2% improvement on unseen domain performance

4% enhancement in adaptation performance

Outperforms state-of-the-art meta-training methods across 7 task settings

Abstract

Adapting large language models (LLMs) to unseen tasks with in-context training samples without fine-tuning remains an important research problem. To learn a robust LLM that adapts well to unseen tasks, multiple meta-training approaches have been proposed such as MetaICL and MetaICT, which involve meta-training pre-trained LLMs on a wide variety of diverse tasks. These meta-training approaches essentially perform in-context multi-task fine-tuning and evaluate on a disjointed test set of tasks. Even though they achieve impressive performance, their goal is never to compute a truly general set of parameters. In this paper, we propose MAML-en-LLM, a novel method for meta-training LLMs, which can learn truly generalizable parameters that not only perform well on disjointed tasks but also adapts to unseen tasks. We see an average increase of 2% on unseen domains in the performance while a massive 4% improvement on adaptation performance. Furthermore, we demonstrate that MAML-en-LLM outperforms baselines in settings with limited amount of training data on both seen and unseen domains by an average of 2%. Finally, we discuss the effects of type of tasks, optimizers and task complexity, an avenue barely explored in meta-training literature. Exhaustive experiments across 7 task settings along with two data settings demonstrate that models trained with MAML-en-LLM outperform SOTA meta-training approaches.