Papers by Ananya Malik
Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model’s Empathy (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models’ ability to converse naturally is empowered by their ability to empathetically understand and respond to their users. |
| Approach: | They propose a framework to investigate how LLMs’ cognitive and affective empathy vary across user personas defined by intersecting demographic attributes. |
| Outcome: | The proposed framework examines 315 unique personas from age, culture, and gender across four LLMs. |
Who Speaks Matters: Analysing the Influence of the Speaker’s Linguistic Identity on Hate Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models are known to be brittle and biased against marginalised communities and dialects. |
| Approach: | They investigate the robustness of hate speech classification using LLMs when explicit and implicit markers of the speaker’s ethnicity are injected into the input. |
| Outcome: | The proposed model is robust when explicit and implicit markers of speaker's ethnicity are injected into the input. |