Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Jihyeon, Kim, Dain, Jung, Doohae, Kim, Boseop, On, Kyoung-Woon
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916370358206464
author Lee, Jihyeon
Kim, Dain
Jung, Doohae
Kim, Boseop
On, Kyoung-Woon
author_facet Lee, Jihyeon
Kim, Dain
Jung, Doohae
Kim, Boseop
On, Kyoung-Woon
contents In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in methods that rely on weight updates. Recently, a few studies have demonstrated the feasibility of few-shot learning with seq2seq models; however, this has been limited to tasks that align well with the seq2seq architecture, such as summarization and translation. Inspired by these initial studies, we provide a first-ever extensive experiment comparing the in-context few-shot learning capabilities of decoder-only and encoder-decoder models on a broad range of tasks. Furthermore, we propose two methods to more effectively elicit in-context learning ability in seq2seq models: objective-aligned prompting and a fusion-based approach. Remarkably, our approach outperforms a decoder-only model that is six times larger and exhibits significant performance improvements compared to conventional seq2seq models across a variety of settings. We posit that, with the right configuration and prompt design, seq2seq models can be highly effective few-shot learners for a wide spectrum of applications.
format Preprint
id arxiv_https___arxiv_org_abs_2307_14856
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners
Lee, Jihyeon
Kim, Dain
Jung, Doohae
Kim, Boseop
On, Kyoung-Woon
Computation and Language
Artificial Intelligence
In-context learning, which offers substantial advantages over fine-tuning, is predominantly observed in decoder-only models, while encoder-decoder (i.e., seq2seq) models excel in methods that rely on weight updates. Recently, a few studies have demonstrated the feasibility of few-shot learning with seq2seq models; however, this has been limited to tasks that align well with the seq2seq architecture, such as summarization and translation. Inspired by these initial studies, we provide a first-ever extensive experiment comparing the in-context few-shot learning capabilities of decoder-only and encoder-decoder models on a broad range of tasks. Furthermore, we propose two methods to more effectively elicit in-context learning ability in seq2seq models: objective-aligned prompting and a fusion-based approach. Remarkably, our approach outperforms a decoder-only model that is six times larger and exhibits significant performance improvements compared to conventional seq2seq models across a variety of settings. We posit that, with the right configuration and prompt design, seq2seq models can be highly effective few-shot learners for a wide spectrum of applications.
title Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2307.14856