Bridging the meaning gap: A computational approach to semantic variation

该项目旨在创建和验证一类新的大型语言模型，这些模型可以捕获并部分解释人与人之间的语义差异。我们将（1）测量个体之间词义和语言经验的细微差异;（2）开发包含这种变化的计算模型;（3）评估模型在多大程度上捕获与政治派别，性别和文化相关的行为和认知差异。这将促进我们对个体差异的性质和起源的理解，并改善人工智能系统对代表性不足群体的校准。这些进展将支持在卫生、国内安全和对错误信息的复原力方面的最终应用成果。

This project aims to create and validate a new class of large language models that capture and partially explain semantic variation between people. We will (1) measure nuanced differences in word meaning and linguistic experience across individuals; (2) develop computational models that incorporate this variation; and (3) evaluate the extent to which the models capture behavioural and cognitive differences related to political affiliation, gender, and culture. This will advance our understanding of the nature and origin of individual differences as well as improve the calibration of AI systems for under-represented groups. These advances will support eventual applied outcomes in health, domestic security, and resilience to misinformation.