Summary of Silent Signals, Loud Impact: Llms For Word-sense Disambiguation Of Coded Dog Whistles, by Julia Kruk et al.
Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles
by Julia Kruk, Michela Marchini, Rijul Magu, Caleb Ziems, David Muchlinski, Diyi Yang
First submitted to arxiv on: 10 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach utilizes Large Language Models (LLMs) to disambiguate dog whistles from standard speech, creating a dataset of 16,550 high-confidence coded examples. This technique can be applied in hate speech detection, neology, and political science. The paper presents an innovative method for word-sense disambiguation, which has significant implications for understanding and combating discrimination. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers created a massive dataset called Silent Signals to help identify and combat dog whistles in social media and politics. Dog whistling is a way to secretly communicate racist or discriminatory ideas without getting caught. The new technique uses big language models to figure out when someone is using code words to mean something bad. This can be used to improve hate speech detection systems and better understand how discrimination happens. |
