21 citations · 31 across the 15 of their papers we have counts for
9 papers · 1 filter
Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
Rebecca Dorn, Lee Kezar, Fred Morstatter +1
Content moderation on social media platforms shapes the dynamics of online discourse, influencing whose voices are amplified and whose are suppressed. Recent studies have raised co…
Secret Keepers: The Impact of LLMs on Linguistic Markers of Personal Traits
Zhivar Sourati, Meltem Ozcan, Colin McDaniel +5
Prior research has established associations between individuals' language usage and their personal traits; our linguistic patterns reveal information about our personalities, emoti…
Risk and Response in Large Language Models: Evaluating Key Threat Categories
Bahareh Harandizadeh, Abel Salinas, Fred Morstatter
This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward mode…
Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations
Abhishek Anand, Negar Mokhberian, Prathyusha Naresh Kumar +5
Researchers have raised awareness about the harms of aggregating labels especially in subjective tasks that naturally contain disagreements among human annotators. In this work we…
"Define Your Terms" : Enhancing Efficient Offensive Speech Classification with Definition
Huy Nghiem, Umang Gupta, Fred Morstatter
The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet s…
The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance
Abel Salinas, Fred Morstatter
Large Language Models (LLMs) are regularly being used to label data across many domains and for myriad tasks. By simply asking the LLM for an answer, or ``prompting,'' practitioner…