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.
Julia Kruk, Michela Marchini, Rijul Magu, Caleb Ziems, David Muchlinski, and Diyi Yang. 2024.Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12493–12509, Bangkok, Thailand. Association for Computational Linguistics.
@inproceedings{kruk-etal-2024-silent, title = "Silent Signals, Loud Impact: {LLM}s for Word-Sense Disambiguation of Coded Dog Whistles", author = "Kruk, Julia and Marchini, Michela and Magu, Rijul and Ziems, Caleb and Muchlinski, David and Yang, Diyi", editor = "Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek", booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = aug, year = "2024", address = "Bangkok, Thailand", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.acl-long.675/", doi = "10.18653/v1/2024.acl-long.675", pages = "12493--12509", abstract = "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."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="kruk-etal-2024-silent"> <titleInfo> <title>Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles</title> </titleInfo> <name type="personal"> <namePart type="given">Julia</namePart> <namePart type="family">Kruk</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Michela</namePart> <namePart type="family">Marchini</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Rijul</namePart> <namePart type="family">Magu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Caleb</namePart> <namePart type="family">Ziems</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">David</namePart> <namePart type="family">Muchlinski</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Diyi</namePart> <namePart type="family">Yang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2024-08</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title> </titleInfo> <name type="personal"> <namePart type="given">Lun-Wei</namePart> <namePart type="family">Ku</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Andre</namePart> <namePart type="family">Martins</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Vivek</namePart> <namePart type="family">Srikumar</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Bangkok, Thailand</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>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.</abstract> <identifier type="citekey">kruk-etal-2024-silent</identifier> <identifier type="doi">10.18653/v1/2024.acl-long.675</identifier> <location> <url>https://aclanthology.org/2024.acl-long.675/</url> </location> <part> <date>2024-08</date> <extent unit="page"> <start>12493</start> <end>12509</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles%A Kruk, Julia%A Marchini, Michela%A Magu, Rijul%A Ziems, Caleb%A Muchlinski, David%A Yang, Diyi%Y Ku, Lun-Wei%Y Martins, Andre%Y Srikumar, Vivek%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)%D 2024%8 August%I Association for Computational Linguistics%C Bangkok, Thailand%F kruk-etal-2024-silent%X 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.%R 10.18653/v1/2024.acl-long.675%U https://aclanthology.org/2024.acl-long.675/%U https://doi.org/10.18653/v1/2024.acl-long.675%P 12493-12509
[Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles](https://aclanthology.org/2024.acl-long.675/) (Kruk et al., ACL 2024)
Julia Kruk, Michela Marchini, Rijul Magu, Caleb Ziems, David Muchlinski, and Diyi Yang. 2024.Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12493–12509, Bangkok, Thailand. Association for Computational Linguistics.