Harshit Joshi

Stanford University

Stanford, CA, USA

Email: harshitj at stanford dot edu

Harshit Joshi (हर्षित जोशी)

I'm a third-year CS PhD student at Stanford University with the StanfordNLP group and OVAL lab, advised by Prof. Monica Lam. I'm currently interested in creating systems that assist users and researchers to leverage LLMs for gathering and curating knowledge — see 🍔 SLIDERS and 🤖 Genie Worksheets.

Previously, I was a Research Fellow at Microsoft Research with the PROSE group, where I worked on Program Repair and Formula Intelligence in Excel spreadsheets, advised by Dr. José Cambronero and Dr. Vu Le.

If you're an undergrad/master's student at Stanford interested in research, please reach out! I'm more than happy to chat about opportunities here!

News

Apr 24, 2026

New paper: 🍔 SLIDERS — Scalable QA over Long Document Sets. Link

Jun 12, 2025

Quoted in The Economist article "Can India be an AI winner?" discussing AI developments in India. Link

May 15, 2025

Genie Worksheets is accepted to ACL 2025 (See you in Vienna!)

Feb 14, 2025

Gave a talk at The First Workshop of a Public AI Assistant to World Wide Knowledge (WWK) on Genie Worksheets. Link Video Image

Mar 19, 2024

Aligned with Prof. Monica Lam, excited to be working on conversational agents for the real world!

Publications

2024

FLAME: A small language model for spreadsheet formulas

H. Joshi, A. Ebenezer, J. Cambronero, S. Gulwani, A. Kanade, V. Le, I. Radicek, G. VerbruggenAAAI 2024

project pagearxivmedia

2023

Repair Is Nearly Generation: Multilingual Program Repair with LLMs

H. Joshi, J. Cambronero, S. Gulwani, A. Kanade, V. Le, I. Radicek, G. VerbruggenAAAI 2023

project pagearxiv

Blog Posts

May 1, 2022Undergrad at Cluster Innovation Center