2024/06/10 by Julia Kruk, Michela Marchini, Kruk, Julia +8 · 1 citation
Computer Science · Social Sciences · #Artificial Intelligence in Law #Computation and Language (cs.CL) #FOS: Computer and information sciences #J.4 #K.4.1 #K.4.2 #Law, AI, and Intellectual Property #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2406.06840
openalex publication_date 2024/06/10 · openalex created_date 2024/06/13 · openalex updated_date 2026/07/28
A dog whistle is a form of coded communication that carries a secondary meaning to specific audiences and is often weaponized for racial and socioeconomic discrimination. Dog whistling historically originated from United States politics, but in recent years has taken root in social media as a means of evading hate speech detection systems and maintaining plausible deniability. In this paper, we present an approach for word-sense disambiguation of dog whistles from standard speech using Large Language Models (LLMs), and leverage this technique to create a dataset of 16,550 high-confidence coded examples of dog whistles used in formal and informal communication. Silent Signals is the largest dataset of disambiguated dog whistle usage, created for applications in hate speech detection, neology, and political science. The dataset can be found at https://huggingface.co/datasets/SALT-NLP/silentsignals.