How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes

Anonymous

TL;DR: This paper examines how different curriculum learning strategies affect Transformer's in-context learning capability on multiple function classes.

Abstract: Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text, also known as in-context learning (ICL). While recent work has attempted to understand the mechanisms driving ICL, few have explored training strategies that incentivize these models to generalize to multiple tasks. Multi-task learning (MTL) for generalist models is a promising direction that offers transfer learning potential, enabling large parameterized models to be trained from simpler, related tasks. In this work, we investigate the combination of MTL with ICL to build models that efficiently learn tasks while being robust to out-of-distribution examples. We propose several effective curriculum learning strategies that allow ICL models to achieve higher data efficiency and more stable convergence. Our experiments reveal that ICL models can effectively learn difficult tasks by training on progressively harder tasks while mixing in prior tasks, denoted as mixed curriculum in this work.

Paper Type: short

Research Area: Interpretability and Analysis of Models for NLP

Contribution Types: Model analysis & interpretability, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English