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 2306.08158cs.CLcs.AIcs.LG
收藏

语言模型中的社会人口统计偏差:综述与未来方向

Sociodemographic Bias in Language Models: A Survey and Forward Path

Pennsylvania State University(宾夕法尼亚州立大学)

Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson, Rebecca J. Passonneau

AI总结:

该综述梳理了过去十年语言模型社会人口统计偏差的研究,按偏差类型、量化、去偏差分类,追踪后两者演进,指出趋势局限与新兴技术,给出开放问题清单以指引未来研究。

摘要:

语言模型(LMs)中的社会人口统计偏差在实际场景部署时可能造成危害。本文对过去十年间语言模型社会人口统计偏差的相关研究开展了全面综述,构建了一套分类体系以梳理不同研究目标:偏差类型、偏差量化方法及去偏差技术。我们追踪了后两类研究方向的演进历程,进而指出现有研究趋势及其局限性,同时介绍了新兴技术。为引导未来研究产出更有效、更可靠的解决方案,并帮助研究者在该广阔领域中定位自身工作,我们最后列出了待解决问题的清单。

英文摘要:

Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a typology that facilitates examining the different aims: types of bias, quantifying bias, and debiasing techniques. We track the evolution of the latter two questions, then identify current trends and their limitations, as well as emerging techniques. To guide future research towards more effective and reliable solutions, and to help authors situate their work within this broad landscape, we conclude with a checklist of open questions.

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。

↑