This is Ashima, a PhD student at UCLA CS advised by Prof. Saadia Gabriel. I was a Deepmind Scholar at the University of California, Los Angeles during my MSCS. I also collaborate with Prof. Nanyun Peng at UCLA NLP.

My research agenda centers on building equitable and socially responsible AI. As humans interact with AI systems, it is imperative to ensure that these models are safe, inclusive and fair. My research achieves this by focusing on a) fair detection of toxicity and harmful behaviors and b) revisiting preference acquisition protocols for robust LLM alignment.

Open Office Hours : Mentorship from my collaborators (Hritik Bansal, Xiao Liu, Gantavya Bhatt, Tanmay Parekh) has been invaluable in shaping my journey, helping me grow both personally and professionally. Now, I’m committed to giving back to the community through 1:1 sessions. If you’d like to chat about research, grad school applications or feedback on essays, please fill out this form.

News

🍄 September 2024 QUDSELECT is accepted at ✨EMNLP 2024✨! I will be in Miami, Florida 11 Nov - 17 Nov, 2024. Checkout publications from my peers - Misinformation Interventions by LLMs, LLMs for Mental Health Support, Knowledge Transfer for Fact Verfication !!

🍄 September 2024 Joining MARS Lab with Genglin Liu, Salman Rahman and Sheriff Issaka.

Service

• Programme Committee / Reviewer: ICLR Tiny Papers 2024, SoCal NLP Symposium 2023, Neurips D&B 2024