Towards Continual Knowledge Learning of Language ModelsDownload PDF

Published: 28 Jan 2022, Last Modified: 22 Oct 2023ICLR 2022 PosterReaders: Everyone
Keywords: continual learning, knowledge acquisition, catastrophic forgetting, large language models, pretraining, natural language processing
Abstract: Large Language Models (LMs) are known to encode world knowledge in their parameters as they pretrain on a vast amount of web corpus, which is often utilized for performing knowledge-dependent downstream tasks such as question answering, fact-checking, and open dialogue. In real-world scenarios, the world knowledge stored in the LMs can quickly become outdated as the world changes, but it is non-trivial to avoid catastrophic forgetting and reliably acquire new knowledge while preserving invariant knowledge. To push the community towards better maintenance of ever-changing LMs, we formulate a new continual learning (CL) problem called Continual Knowledge Learning (CKL). We construct a new benchmark and metric to quantify the retention of time-invariant world knowledge, the update of outdated knowledge, and the acquisition of new knowledge. We adopt applicable recent methods from literature to create several strong baselines. Through extensive experiments, we find that CKL exhibits unique challenges that are not addressed in previous CL setups, where parameter expansion is necessary to reliably retain and learn knowledge simultaneously. By highlighting the critical causes of knowledge forgetting, we show that CKL is a challenging and important problem that helps us better understand and train ever-changing LMs.
One-sentence Summary: We propose a novel continual learning formulation named Continual Knowledge Learning which allows large language models to constantly obtain new and updated knowledge while mitigating forgetting of previous learned time-invariant knowledge.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2110.03215/code)
12 Replies

Loading