Oddballs and Misfits: Detecting Implicit Abuse in Which Identity Groups are Depicted as Deviating from the Norm

Warning: This paper contains content that may be offensive or upsetting. We address the task of detecting abusive sentences in which identity groups are depicted as deviating from the norm (e.g. Gays sprinkle flour over their gardens for good luck). These abusive utterances need not be stereotypes or negative in sentiment. For this type of abuse, we are the first to present a study on how to detect it. We introduce datasets for this task created via crowdsourcing that include 7 different identity groups. We also report on classification experiments and show that only large language models detect this abuse reliably.