@inproceedings{gu2023pre-training,
author = {Gu, Yuxian and Dong, Li and Wei, Furu and Huang, Minlie},
title = {Pre-Training to Learn in Context},
booktitle = {ACL 2023},
year = {2023},
month = {July},
abstract = {In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully exploited because language models are not explicitly trained to learn in context. To this end, we propose PICL (Pre-training for In-Context Learning), a framework to enhance the language models' in-context learning ability by pre-training the model on a large collection of "intrinsic tasks" in the general plain-text corpus using the simple language modeling objective. PICL encourages the model to infer and perform tasks by conditioning on the contexts while maintaining task generalization of pre-trained models. We evaluate the in-context learning performance of the model trained with PICL on seven widely-used text classification datasets and the Super-NaturalInstrctions benchmark, which contains 100+ NLP tasks formulated to text generation. Our experiments show that PICL is more effective and task-generalizable than a range of baselines, outperforming larger language models with nearly 4x parameters. The code is publicly available at GitHub.},
url = {http://approjects.co.za/?big=en-us/research/publication/pre-training-to-learn-in-context/},
}