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. During my PhD, I’ve been fortunate to spend time at Amazon Alexa AI, ASAPP Inc., and the Aristo team at AI2. 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.

My primary research interest is making large language models and agents better in-context learners and reasoners. Apart from this, I’m also interested in systematic generalization, semantic parsing, question-answering, retrieval, and knowledge distillation. My research has been recognized with a Best Paper Award at NAACL-SRW 2024 and I will be serving on the Program Committee for the AI and Scientific Discovery Workshop at NAACL 2025.

news

Nov 05, 2024 After missing out on both NAACL and ICML 2024, due to an accident, finally attending my first conference for the year! I’ll be in Florida from Nov 9 to Nov 14 for EMNLP 2024. Looking forward to catching up with everyone and chatting about the latest language agents research! 😁
Sep 30, 2024 Resumed my internship with the Aristo team @ AI2. I will continue to work on In-Context Learning for Language Model Agents. 💪 🤖
Jun 19, 2024 GistScore won the Best Paper Award at NAACL-SRW 2024!! 🎉 💪
May 01, 2024 Our paper on GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks got accepted at ICML 2024 – the first ICML paper of my PhD! 🎉
Apr 26, 2024 Our paper on GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks got accepted at NAACL-SRW 2024 as well as the ME-FoMo Workshop at ICLR! 🎉

selected publications

  1. ICML
    GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
    Shivanshu GuptaClemens Rosenbaum, and Ethan R. Elenberg
    Jul 2024
  2. NAACL
    Leveraging Code to Improve In-Context Learning for Semantic Parsing
    Ben Bogin*Shivanshu Gupta*Peter Clark, and 1 more author
    Jun 2024
  3. Coverage-based Example Selection for In-Context Learning
    Shivanshu GuptaMatt Gardner, and Sameer Singh
    Dec 2023
  4. Successive Prompting for Decomposing Complex Questions
    Dheeru DuaShivanshu GuptaSameer Singh, and 1 more author
    Dec 2022