hello!
I’m Prabhav Singh (pronounced Pruh-bhav).
I am a first-year Ph.D. student at UT Austin, advised by Prof. Elias Stengel-Eskin and Prof. Jessy Li.
Before joining UT, I received my MS in Computer Science with a specialization in Human Language Technologies from Johns Hopkins University and the Center for Language and Speech Processing (CLSP). I was fortunate to be advised by Prof. Jason Eisner and Prof. Jesus Villalba.
Before that, I earned my Bachelor’s in Electrical Engineering from Delhi University, where I worked with Prof. K.P.S. Rana and Prof. Vineet Kumar at the APC Lab, NSIT.
You can find more details in my CV. Feel free to reach out at: prabhavs@cs.utexas.edu.
Research Interests
I am interested in computational linguistics, with an emphasis on approaches that are adaptable to supervision constraints and aligned with how humans naturally teach, label, and reason. Specifically, this boils dow to:
-
Clarification, Uncertainty & Attribution: Studying how models navigate ambiguous conversations: knowing when and how to seek clarification, expressing uncertainty and underspecification.
-
Human-AI Collaboration: Building frameworks that optimize decisions in human-LLM workflows, determining when human judgment is needed versus when LLMs suffice (See this and this).
-
Reasoning in LLMs: Understanding and surfacing uncertainty in LLM reasoning, and grounding reasoning chains in relevant documents from the model’s training data.
Previous Interests
I began my research journey with emotion recognition, and while I’ve developed a fair amount of expertise in that space. I was also drawn to speaker recognition and diarization. I found diarization particularly interesting — it's a fundamental speech task with open challenges in temporal structure, multimodal fusion, and low-resource adaptation. I also dabbled in mulimodality: Fusing audio, text, and vision to solve tasks that are natural for humans — but hard for machines. Some of my papers in this field are: