Shramay Palta

Ph.D. Student in Computer Science | NLP Researcher

Shramay.jpeg

Iribe 4108

8125 Paint Branch Dr, College Park, MD 20742

spalta[at]umd[dot]edu

I am a fourth year Ph.D. Student in the Department of Computer Science at the University of Maryland, College Park where I am advised by Professor Rachel Rudinger.

I am a member of the Computational Linguistics and Information Processing (CLIP) Lab in UMIACS.

My research interests broadly lie in the areas of Computational Linguistics and Natural Language Processing with a focus on Commonsense Reasoning, Explainability and Interpretability, and Bias and Fairness in NLP. Specifically, I try to explore and understand:

  1. Is commonsense reasoning prone to uncertainty?
  2. How do humans and language models behave under this uncertainty?
  3. Are there cases where models deviate from human values and notions about the real world?

I got my Master of Science in Computer Science from UMD in 2023. Before coming to Maryland, I graduated from Birla Institute of Technology and Science (BITS), Pilani in 2021 with a Bachelor of Engineering (B.E.) in Electrical and Electronics Engineering.

For Summer 2025, I will be a research intern in the Office AI group at Microsoft Research, where I will be working with Michael Bentley and Mengting Wan.

News

Feb 26, 2025 I will be joining Microsoft Research as a Research Intern over the Summer working with Michael Bentley, Mengting Wan and the Office AI Team!
Feb 26, 2025 New preprint on LLM (mis)alignment from my internship at Microsoft Research! View it here: Speaking the Right Language: The Impact of Expertise Alignment in User-AI Interactions.
Sep 20, 2024 One paper accepted to the Findings of EMNLP 2024. View it here: Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning!
Jul 03, 2024 One paper accepted to ECCV 2024. View it here: Investigating Style Similarity in Diffusion Models!
May 28, 2024 Started my internship at Microsoft Research.

Selected Publications

  1. Speaking the Right Language: The Impact of Expertise Alignment in User-AI Interactions
    Shramay Palta, Nirupama Chandrasekaran , Rachel Rudinger , and Scott Counts
    2025
  2. Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning
    Shramay Palta, Nishant Balepur , Peter A. Rankel , Sarah Wiegreffe , and 2 more authors
    In Findings of the Association for Computational Linguistics: EMNLP 2024 , Nov 2024
  3. Investigating Style Similarity in Diffusion Models
    Gowthami Somepalli , Anubhav Gupta , Kamal Gupta , Shramay Palta, and 4 more authors
    In Computer Vision – ECCV 2024 , Nov 2025
  4. It’s Not Easy Being Wrong: Large Language Models Struggle with Process of Elimination Reasoning
    Nishant Balepur , Shramay Palta, and Rachel Rudinger
    In Findings of the Association for Computational Linguistics ACL 2024 , Aug 2024
  5. FORK: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning Models
    Shramay Palta, and Rachel Rudinger
    In Findings of the Association for Computational Linguistics: ACL 2023 , Jul 2023