1 citations · 2 across the 4 of their papers we have counts for
5 papers
Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation
Ananya Malik, Mai ElSherief
Large Language Models (LLMs) can adopt distinct personas to tune their semantics, expertise, and perspective to different users and tasks. Precise control over these traits is crit…
"He gets to be the fun parent": Understanding and Supporting Burnt-Out Mothers in Online Communities
Nazanin Sabri, Ananya Malik, Bangzhao Shu +3
Maternal burnout is a psychological phenomena with documented harms to both mother and child, requiring prompt attention. Mothers experiencing burnout might choose to turn to onlin…
Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy
Ananya Malik, Nazanin Sabri, Melissa Karnaze +1
Large Language Models' (LLMs) ability to converse naturally is empowered by their ability to empathetically understand and respond to their users. However, emotional experiences ar…
Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classification
Ananya Malik, Kartik Sharma, Shaily Bhatt +1
Large Language Models (LLMs) offer a lucrative promise for scalable content moderation, including hate speech detection. However, they are also known to be brittle and biased again…
Evaluating Large Language Models through Gender and Racial Stereotypes
Ananya Malik
Language Models have ushered a new age of AI gaining traction within the NLP community as well as amongst the general population. AI's ability to make predictions, generations and…