Nationality Bias in Text Generation

Nationality Bias in Text Generation
复制标题

文本生成中的国籍偏见

DOI:
10.48550/arxiv.2302.02463
复制
发表时间:
2023
影响因子:
2.8
通讯作者:
Shomir Wilson
Shomir Wilson
中科院分区:
医学4区
文献类型:
--
作者:
Pranav Narayanan Venkit;Sanjana Gautam;Ruchi Panchanadikar;Ting;Shomir Wilson

文献摘要

参考文献

被引文献

相似文献

很少有人关注语言模型中的国籍偏见分析,特别是当国籍被高度用作提高社会NLP模型性能的一个因素时。本文研究了文本生成模型GPT-2如何强调基于国家的恶魔的预先存在的社会偏见。我们使用GPT-2为不同国籍的人制作故事,并使用敏感性分析来探索互联网用户数量和国家经济状况如何影响故事的情绪。为了通过大型语言模型(LLM)减少偏见的传播,我们探索了对抗性触发的去偏见方法。我们的研究结果表明,GPT-2对互联网用户较少的国家表现出明显的偏见,而对抗性触发有效地减少了这种偏见。
Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country’s economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore the debiasing method of adversarial triggering. Our results show that GPT-2 demonstrates significant bias against countries with lower internet users, and adversarial triggering effectively reduces the same.
将仇恨言论分类器与事后解释结合起来
DOI: 10.18653/v1/2020.acl-main.483
发表时间: 2020
期刊: Proceedings of the Annual Meeting of the Association for Computational Linguistics
影响因子: --
作者:
Kennedy, Brendan;Jin, Xisen;Mostafazadeh Davani, Aida;Dehghani, Morteza;Ren, Xiang
通讯作者: Ren, Xiang
DOI: 10.18653/v1/d19-1221
发表时间: 2019-08
期刊: --
影响因子: --
作者:
Eric Wallace;Shi Feng;Nikhil Kandpal;Matt Gardner;Sameer Singh
通讯作者: Eric Wallace;Shi Feng;Nikhil Kandpal;Matt Gardner;Sameer Singh
论 NLP 中的偏见和危害的衡量
DOI: --
发表时间: 2022
期刊: Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
影响因子: --
作者:
Sunipa Dev;Emily Sheng;Jieyu Zhao;Aubrie Amstutz;Jiao Sun;Yu Hou;Mattie Sanseverino;Jiin Kim;Akihiro Nishi;Nanyun Peng
通讯作者: Nanyun Peng