Elastic weight consolidation for better bias inoculation
Abstract
The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification. While fine-tuning models on additional data has been used to mitigate them, a common issue is that of catastrophic forgetting of the original training dataset. In this paper, we show that elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases while being less susceptible to catastrophic forgetting. In our evaluation on fact verification and NLI stress tests, we show that fine-tuning with EWC dominates standard fine-tuning, yielding models with lower levels of forgetting on the original (biased) dataset for equivalent gains in accuracy on the fine-tuning (unbiased) dataset.
Cite
@article{arxiv.2004.14366,
title = {Elastic weight consolidation for better bias inoculation},
author = {James Thorne and Andreas Vlachos},
journal= {arXiv preprint arXiv:2004.14366},
year = {2021}
}
Comments
Accepted at EACL 2021. Was previously submitted to arxiv with the title "Avoiding catastrophic forgetting in mitigating model biases in sentence-pair classification with elastic weight consolidation"