3 papers
cs.CL2024
Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats
Kuleen Sasse, Carlos Aguirre, Isabel Cachola +2
WARNING: This paper contains content that maybe upsetting or offensive to some readers. Dog whistles are coded expressions with dual meanings: one intended for the general public (…
cs.CL2024
Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation
Shan Chen, Mingye Gao, Kuleen Sasse +6
Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong info…
cs.CL2023
Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models
Carlos Aguirre, Kuleen Sasse, Isabel Cachola +1
Recently, work in NLP has shifted to few-shot (in-context) learning, with large language models (LLMs) performing well across a range of tasks. However, while fairness evaluations…