Manya Wadhwa

picture

Twitter
LinkedIn
Google Scholar
Github
manya.wadhwa[@]utexas.edu
she/her

👩🏻‍💻

I am a first second third year PhD student at the Text Analysis, Understanding, and Reasoning (TAUR) group, at the University of Texas at Austin, led by Professor Greg Durrett. I am also a part of the UT NLP group. My work in my PhD has focused on how to leverage natural language explanations for better evaluation and for post-hoc editing responses for improving factuality. In general, I am interested in how we can have more reliable, adaptive evaluation/alignment techniques that incorporate subjectivity and nuances.

Experience

Previously, I was an Associate Research Engineer with the R&D team at Goldman Sachs for three years. This team was led by Vijay Saraswat. I closely worked with Johannes Hoffart and Luciano Del Corro on problems in the space of Document AI and Conversation Understanding specific to the field of Finance.

I completed my Master's in Computer Science from Johns Hopkins University where I worked with Professor Mark Dredze in Regulatory Document Understanding. I did my undergrad from IIIT-Delhi where I majored in Computer Science.

I am a supporter of minority in tech, if you are looking for guidance on how to navigate the industry/academia, feel free to reach out on linkedin/email and we can schedule a chat! :)

News

August 2024: Learning to Refine accepted to EMNLP 2024 Findings! See you in Miami! 🌴🦩

July 2024: First PhD paper (Explanation-Based Rescaling) accepted to COLM 2024! See you in Philly!

May 2024: Started Internship at Adobe Research, with the Document Intelligence Team!

Research

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Pre-print
Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, Greg Durrett

Learning to Refine with Fine-Grained Natural Language Feedback
Findings of EMNLP 2024
[Code] [Training Data] [Poster]
Manya Wadhwa, Xinyu Zhao, Junyi Jessy Li, Greg Durrett

Using Natural Language Explanations to Rescale Human Judgments
Proceedings of COLM 2024
[Data] [Poster]
Manya Wadhwa, Jifan Chen, Junyi Jessy Li, Greg Durrett

Aligning Public Feedback to Requests for Comments on Regulations.gov
ICWSM 2020
Manya Wadhwa, Silvio Amir, Mark Dredze