arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04220cs.CLcs.AI
收藏

BEADs: 跨领域偏差评估

BEADs: Bias Evaluation Across Domains

Vector Institute(向量研究所);Royal Bank of Canada(皇家银行);University of Toronto(多伦多大学)

Shaina Raza, Mizanur Rahman, Michael R. Zhang

AI总结:

BEADs数据集通过跨领域偏差评估,提供广泛NLP任务的偏差检测与模型评估方案,揭示现有模型在人口群体上的系统性偏差问题。

摘要:

近年来,大规模语言模型(LLMs)的进步显著提升了自然语言处理(NLP)应用的效果。然而,这些模型往往继承并放大了训练数据中的偏差。尽管已有多个用于偏差检测的数据集,但大多数仅限于一到两个NLP任务,通常是分类或评估任务,且不提供在多样化任务设置中的广泛覆盖。为解决这一差距,我们引入了偏差跨领域评估(Bias Evaluations Across Domains,BEADs)数据集,旨在支持广泛的任务,包括文本分类、标记分类、偏差量化和无害语言生成。本工作的一项关键贡献是支持模型评估和监督训练的黄金标准标注方案。在最先进的模型上的实验揭示了一些差距:一些模型对特定人口群体存在系统性偏差,而其他模型在不同群体间应用安全护栏更加严格或不一致。总体而言,这些结果突显了当前模型的持续不足,并强调了全面偏差评估的必要性。项目:https://vectorinstitute.github.io/BEAD/ 数据:https://huggingface.co/datasets/shainar/BEAD

英文摘要:

Recent advances in large language models (LLMs) have substantially improved natural language processing (NLP) applications. However, these models often inherit and amplify biases present in their training data. Although several datasets exist for bias detection, most are limited to one or two NLP tasks, typically classification or evaluation and do not provide broad coverage across diverse task settings. To address this gap, we introduce the \textbf{Bias Evaluations Across Domains} (\textbf{B}\texttt{EADs}) dataset, designed to support a wide range of NLP tasks, including text classification, token classification, bias quantification, and benign language generation. A key contribution of this work is a gold-standard annotation scheme that supports both evaluation and supervised training of language models. Experiments on state-of-the-art models reveal some gaps: some models exhibit systematic bias toward specific demographics, while others apply safety guardrails more strictly or inconsistently across groups. Overall, these results highlight persistent shortcomings in current models and underscore the need for comprehensive bias evaluation. Project: https://vectorinstitute.github.io/BEAD/ Data: https://huggingface.co/datasets/shainar/BEAD

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。

↑