3 accepted papers
We study language ideologies in text produced by LLMs through a case study on English gendered language reform (related to role nouns like congressperson/-woman/-man, and singular they). First, we find political bias: when asked to use language that is “correct” or “natural”, LLMs use language most…
Much work has explored lexical and semantic variation in online communities, and drawn connections to community identity and user engagement patterns. Communities also express identity through the sociolinguistic concept of stancetaking. Large-scale computational work on stancetaking has explored co…
Much research has sought to evaluate the degree to which large language models reflect social biases. We complement such work with an approach to elucidating the connections between language model predictions and people’s social attitudes. We show how word preferences in a large language model refle…