Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914839736090624 |
|---|---|
| author | Kruk, Julia Marchini, Michela Magu, Rijul Ziems, Caleb Muchlinski, David Yang, Diyi |
| author_facet | Kruk, Julia Marchini, Michela Magu, Rijul Ziems, Caleb Muchlinski, David Yang, Diyi |
| contents | 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/silent_signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06840 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles Kruk, Julia Marchini, Michela Magu, Rijul Ziems, Caleb Muchlinski, David Yang, Diyi Computation and Language Machine Learning J.4; K.4.1; K.4.2 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/silent_signals. |
| title | Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles |
| topic | Computation and Language Machine Learning J.4; K.4.1; K.4.2 |
| url | https://arxiv.org/abs/2406.06840 |