Climate Change Data Portal
DOI | 10.1038/s41598-024-51969-w |
Conversational AI and equity through assessing GPT-3's communication with diverse social groups on contentious topics | |
Chen, Kaiping; Shao, Anqi; Burapacheep, Jirayu; Li, Yixuan | |
发表日期 | 2024 |
ISSN | 2045-2322 |
起始页码 | 14 |
结束页码 | 1 |
卷号 | 14期号:1 |
英文摘要 | Autoregressive language models, which use deep learning to produce human-like texts, have surged in prevalence. Despite advances in these models, concerns arise about their equity across diverse populations. While AI fairness is discussed widely, metrics to measure equity in dialogue systems are lacking. This paper presents a framework, rooted in deliberative democracy and science communication studies, to evaluate equity in human-AI communication. Using it, we conducted an algorithm auditing study to examine how GPT-3 responded to different populations who vary in sociodemographic backgrounds and viewpoints on crucial science and social issues: climate change and the Black Lives Matter (BLM) movement. We analyzed 20,000 dialogues with 3290 participants differing in gender, race, education, and opinions. We found a substantively worse user experience among the opinion minority groups (e.g., climate deniers, racists) and the education minority groups; however, these groups changed attitudes toward supporting BLM and climate change efforts much more compared to other social groups after the chat. GPT-3 used more negative expressions when responding to the education and opinion minority groups. We discuss the social-technological implications of our findings for a conversational AI system that centralizes diversity, equity, and inclusion. |
语种 | 英语 |
WOS研究方向 | Science & Technology - Other Topics |
WOS类目 | Multidisciplinary Sciences |
WOS记录号 | WOS:001145797200084 |
来源期刊 | SCIENTIFIC REPORTS
![]() |
文献类型 | 期刊论文 |
条目标识符 | http://gcip.llas.ac.cn/handle/2XKMVOVA/287365 |
作者单位 | University of Wisconsin System; University of Wisconsin Madison; Stanford University; University of Wisconsin System; University of Wisconsin Madison |
推荐引用方式 GB/T 7714 | Chen, Kaiping,Shao, Anqi,Burapacheep, Jirayu,et al. Conversational AI and equity through assessing GPT-3's communication with diverse social groups on contentious topics[J],2024,14(1). |
APA | Chen, Kaiping,Shao, Anqi,Burapacheep, Jirayu,&Li, Yixuan.(2024).Conversational AI and equity through assessing GPT-3's communication with diverse social groups on contentious topics.SCIENTIFIC REPORTS,14(1). |
MLA | Chen, Kaiping,et al."Conversational AI and equity through assessing GPT-3's communication with diverse social groups on contentious topics".SCIENTIFIC REPORTS 14.1(2024). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。