Prasann Singhal
प्रसन्न सिंघल

PhD Student
University of California, Berkeley

prasann [at] berkeley.edu   PrasannS   prasann_singhal   semantic scholar

Hi, I'm Prasann! I'm a first-year PhD student at UC Berkeley, advised by Sewon Min and Jacob Steinhardt. As an undergrad, I was extremely fortunate to be advised by the amazing Greg Durrett at UT Austin (I majored in CS and linguistics), and was supported by many awesome labmates and collaborators.

My research focuses on Natural Language Processing and I'm broadly interested in better understanding how language models work. I've gotten to work on lots of cool stuff, from understanding RLHF, to improving decoding algorithm efficiency.

Prior to research, I've also had the chance to participate in nearly 20 hackathons, and made a lot of fun projects.

I love meeting new people so free to send me an email if you'd like to chat about anything (e.g. related research, unrelated research, just want to say hi)! Likewise, if you're a high-schooler or undergrad anywhere interested in research or grad school, I'm always happy to give advice if you feel it'd be useful.

Publications

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

Liyan Tang, Grace Kim, Xinyu Zhao, Thom Lake, Wenxuan Ding, Fangcong Yin, Prasann Singhal, Manya Wadhwa, Zeyu Leo Liu, Zayne Sprague, Ramya Namuduri, Bodun Hu, Juan Diego Rodriguez, Puyuan Peng, Greg Durrett. arxiv 2025.

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, and Greg Durrett. Proceedings of ICLR 2025.

D2PO: Discriminator-Guided DPO with Response Evaluation Models code

Prasann Singhal, Nathan Lambert, Scott Niekum, Tanya Goyal, and Greg Durrett. Proceedings of COLM 2024.

A Long Way to Go: Investigating Length Correlations in RLHF code

Prasann Singhal, Tanya Goyal, Jiacheng Xu, and Greg Durrett. (Oral Spotlight) Proceedings of COLM 2024.

EEL: Efficiently Encoding Lattices for Reranking code

Prasann Singhal, Jiacheng Xu, Xi Ye, and Greg Durrett. Proceedings of ACL 2023.

Assessing Out-of-Domain Language Model Performance from Few Examples

Prasann Singhal*, Jarad Forristal*, Xi Ye, and Greg Durrett. Proceedings of EACL 2023.

Invited Talks / News

[Dec. 2024] Won the 2025 CRA Outstanding Undergraduate Researcher Award (awardee)!

[Jul. 2024] A Long Way to Go in RLHF @ SEAL Reading Group, Scale AI

[Feb. 2024] A Long Way to Go in RLHF @ UT Austin LIN 393 Seminar

[Nov. 2023] A Long Way to Go in RLHF @ IST & Unbabel Seminar

Experience

Scale AI Research Intern / Part-time Researcher. Summer-Fall 2024.

UT Austin TAUR Lab Undergraduate Research Assistant, Natural Language Processing. Fall 2021-Present.

Service / Teaching

UT CS 388 (NLP) TA (Fall 2024)

UT Austin Directed Reading Program Mentor (Spring 2024)

Founder / Teacher - Katy HACK Initiative: I spent 3 years starting/running CS education programs in local elementary / junior high schools

Volunteer Teacher - I spent a summer teaching English, Computer Fundamentals in a village in Gujarat