arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.02463cs.CLcs.AI
收藏

文本生成中的民族偏见

Nationality Bias in Text Generation

College of Information Sciences and Technology(信息科学与技术学院);Pennsylvania State University(宾夕法尼亚州立大学)

Pranav Narayanan Venkit, Sanjana Gautam, Ruchi Panchanadikar, Ting-Hao 'Kenneth' Huang, Shomir Wilson

摘要:

很少有人关注分析语言模型中的国籍偏见,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。本文探讨了文本生成模型,GPT-2,强调预先存在的社会偏见,基于国家的恶魔。我们使用GPT-2生成不同国籍的故事,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感。为了减少偏见通过大语言模型(LLM)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。

英文摘要:

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.

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。

↑