Shivanshu Gupta

PhD Student. University of California, Irivne.

me-2.jpg

I’m a Computer Science Ph.D. Candidate at the University of California Irvine advised by Sameer Singh and working in the areas of Natural Language Processing and Machine Learning. My primary research interests are improving the systematic generalization and multi-step reasoning capabilities of NLP models. I’m also interested in semantic parsing, question answering, and knowledge distillation. Prior to this I worked as a Research Fellow at LinkedIn and Microsoft Research India under the advisership of Prateek Jain, and completed my B.Tech. and M.Tech. in Computer Science from IIT Delhi where I was advised by Mausam. I have also spent some time at Amazon Alexa AI.

news

Nov 17, 2023 Attending the SoCal NLP Symposium 2023 in UCLA!
Nov 15, 2023 Two new preprints: GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks and Leveraging Code to Improve In-context Learning for Semantic Parsing! 🎉
Oct 7, 2023 Our paper on Coverage-based Example Selection for In-Context Learning got accepted at EMNLP Findings 2023 as a long paper! 🎉
Jun 26, 2023 Started summer internship at ASAPP Inc. as a Research Scientist Intern. Working with Ethan Elenberg and Clemens Rosenbaum on gisting for LLMs.
Mar 15, 2023 Passed my candidacy exam! I’m now a PhD Candidate! 🎉

selected publications

  1. ArXiv
    GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
    Shivanshu GuptaClemens Rosenbaum, and Ethan R. Elenberg
    2023
  2. ArXiv
    Leveraging Code to Improve In-context Learning for Semantic Parsing
    Ben BoginShivanshu GuptaPeter Clark, and 1 more author
    2023
  3. ArXiv
    Coverage-based Example Selection for In-Context Learning
    Shivanshu GuptaMatt Gardner, and Sameer Singh
    May 2023
  4. Successive Prompting for Decomposing Complex Questions
    Dheeru DuaShivanshu GuptaSameer Singh, and 1 more author
    Dec 2022