Language model debiasing has emerged as an important field of study in the
NLP community. Numerous debiasing techniques were proposed, but bias ablation
remains an unaddressed issue. We demonstrate a novel framework for inspecting
bias in pre-trained transformer-based language models via movement pruning.
Given a model and a debiasing objective, our framework finds a subset of the
model containing less bias than the original model. We implement our framework
by pruning the model while fine-tuning it on the debiasing objective. Optimized
are only the pruning scores - parameters coupled with the model's weights that
act as gates. We experiment with pruning attention heads, an important building
block of transformers: we prune square blocks, as well as establish a new way
of pruning the entire heads. Lastly, we demonstrate the usage of our framework
using gender bias, and based on our findings, we propose an improvement to an
existing debiasing method. Additionally, we re-discover a bias-performance
trade-off: the better the model performs, the more bias it contains.

本研究提出了一种通过运动剪枝实现检查预训练变压器语言模型中偏差的方法，并使用性别偏见作为案例来验证方法。

探究使用运动修剪在预训练基于 Transformer 的语言模型中的性别偏见

Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning

Magnitude pruning is a widely used strategy for reducing model size in pure
supervised learning; however, it is less effective in the transfer learning
regime that has become standard for state-of-the-art natural language
processing applications. We propose the use of movement pruning, a simple,
deterministic first-order weight pruning method that is more adaptive to
pretrained model fine-tuning. We give mathematical foundations to the method
and compare it to existing zeroth- and first-order pruning methods. Experiments
show that when pruning large pretrained language models, movement pruning shows
significant improvements in high-sparsity regimes. When combined with
distillation, the approach achieves minimal accuracy loss with down to only 3%
of the model parameters.

本文提出一种基于移动修剪的权重修剪方法，相比于纯监督学习中使用的幅度修剪方法，更适用于预训练模型微调，实验证明在高稀疏度下，此方法对预训练语言模型的剪枝效果更好，结合蒸馏技术最大程度地减小模型参数，同时保持模型准确率。