用任务算术思想提取偏见向量，无需标注数据即可降低语言模型偏见。
Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
- 通过对比有偏与预训练模型权重差值，构造偏见向量
- 在SEAT上平均提升0.177分，且不损害下游任务性能
- 适用于希望无监督调优模型公平性的研究人员
近年来语言模型应用广泛，但其输出中反映的训练数据偏见引发社会问题。受任务算术启发，本文提出“偏见向量”方法以缓解该问题。该方法无需人工标注的去偏数据，主要步骤为：(1) 在有偏数据上对预训练语言模型进行持续掩码语言建模训练；(2) 构造偏见向量为有偏模型与预训练模型权重之差；(3) 将偏见向量从预训练模型权重中减去实现去偏。我们在三个语言模型上评估了该方法在SEAT上的表现，平均提升0.177分。实验表明，该方法未降低模型在GLUE基准上的下游任务性能。此外，我们分析了控制偏见向量幅度的缩放因子对SEAT效果的影响，并在SEAT和GLUE上进行了全面评估。
原文摘要 · Abstract (English)
The use of language models (LMs) has increased considerably in recent years, and the biases and stereotypes in training data that are reflected in the LM outputs are causing social problems. In this paper, inspired by the task arithmetic, we propose the ``Bias Vector'' method for the mitigation of these LM biases. The Bias Vector method does not require manually created debiasing data. The three main steps of our approach involve: (1) continual training the pre-trained LMs on biased data using masked language modeling; (2) constructing the Bias Vector as the difference between the weights of the biased LMs and those of pre-trained LMs; and (3) subtracting the Bias Vector from the weights of the pre-trained LMs for debiasing. We evaluated the Bias Vector method on the SEAT across three LMs and confirmed an average improvement of 0.177 points. We demonstrated that the Bias Vector method does not degrade the LM performance on downstream tasks in the GLUE benchmark. In addition, we examined the impact of scaling factors, which control the magnitudes of Bias Vectors, with effect sizes on the SEAT and conducted a comprehensive evaluation of our debiased LMs across both the SEAT and GLUE benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。