坍缩的语言模型促进公平性
Collapsed Language Models Promote Fairness
AI总结：
本文通过评估公平性相关词汇上的神经坍缩现象，发现去偏语言模型在词元表示和词嵌入间存在坍缩对齐，并据此提出一种原理性微调方法，能在保持标准任务性能的同时广泛提升去偏方法的公平性。
摘要：
为了缓解近期成功的预训练语言模型中隐式编码的社会偏见，人们提出了多种方法来促进模型公平性，侧重于提示、数据增强、正则化微调等。尽管取得了进展，但要实现对公平性的原理性理解以及一种能持续对语言模型去偏的有效算法并非易事。在本研究中，通过对公平性相关词汇进行神经坍缩（Neural Collapse，深度网络最后一层表示和分类器中出现的一种学习现象）的严格评估，我们发现去偏后的语言模型在词元表示和词嵌入之间表现出坍缩的对齐。更重要的是，这一观察启发我们设计了一种原理性的微调方法，该方法能在广泛的各种去偏方法中有效提升公平性，同时仍保持语言模型在标准自然语言理解任务上的性能。我们在 https://github.com/Xujxyang/Fairness-NC-main 附上了代码。
英文摘要：
To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning, and more. Despite the development, it is nontrivial to reach a principled understanding of fairness and an effective algorithm that can consistently debias language models. In this work, by rigorous evaluations of Neural Collapse -- a learning phenomenon happen in last-layer representations and classifiers in deep networks -- on fairness-related words, we find that debiased language models exhibit collapsed alignment between token representations and word embeddings. More importantly, this observation inspires us to design a principled fine-tuning method that can effectively improve fairness in a wide range of debiasing methods, while still preserving the performance of language models on standard natural language understanding tasks. We attach our code at https://github.com/Xujxyang/Fairness-NC-main.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
