Saved in:
Bibliographic Details
Main Authors: Sinha, Sanchit, Yue, Yuguang, Soto, Victor, Kulkarni, Mayank, Lu, Jianhua, Zhang, Aidong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.11446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914802326044672
author Sinha, Sanchit
Yue, Yuguang
Soto, Victor
Kulkarni, Mayank
Lu, Jianhua
Zhang, Aidong
author_facet Sinha, Sanchit
Yue, Yuguang
Soto, Victor
Kulkarni, Mayank
Lu, Jianhua
Zhang, Aidong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning
Sinha, Sanchit
Yue, Yuguang
Soto, Victor
Kulkarni, Mayank
Lu, Jianhua
Zhang, Aidong
Computation and Language
Machine Learning
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.
title MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2405.11446