Graceful Forgetting in Generative Language Models

TL;DR

This paper introduces a novel framework called Learning With Forgetting (LWF) that improves fine-tuning of generative language models by selectively unlearning irrelevant knowledge to enhance performance.

Contribution

It adapts the concept of graceful forgetting to generative language models using Fisher Information Matrix weighting for better fine-tuning outcomes.

Findings

Applying LWF improves fine-tuning performance of language models.

Knowledge with high forgetting confidence is periodically unlearned.

The framework demonstrates benefits despite the complexity of knowledge interactions.

Abstract

Recently, the pretrain-finetune paradigm has become a cornerstone in various deep learning areas. While in general the pre-trained model would promote both effectiveness and efficiency of downstream tasks fine-tuning, studies have shown that not all knowledge acquired during pre-training is beneficial. Some of the knowledge may actually bring detrimental effects to the fine-tuning tasks, which is also known as negative transfer. To address this problem, graceful forgetting has emerged as a promising approach. The core principle of graceful forgetting is to enhance the learning plasticity of the target task by selectively discarding irrelevant knowledge. However, this approach remains underexplored in the context of generative language models, and it is often challenging to migrate existing forgetting algorithms to these models due to architecture incompatibility. To bridge this gap, in this paper we propose a novel framework, Learning With Forgetting (LWF), to achieve graceful forgetting in generative language models. With Fisher Information Matrix weighting the intended parameter updates, LWF computes forgetting confidence to evaluate self-generated knowledge regarding the forgetting task, and consequently, knowledge with high confidence is periodically unlearned during fine-tuning. Our experiments demonstrate that, although thoroughly uncovering the mechanisms of knowledge interaction remains challenging in pre-trained language models, applying graceful forgetting can contribute to enhanced fine-tuning performance.