Harshit Joshi (हर्षित जोशी)
I'm a second-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 useful systems that assist users to leverage capabilities of Large Language Models for gathering and creating knowledge.
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
Jun 12, 2025 (1mo ago)
Quoted in The Economist article "Can India be an AI winner?" discussing AI developments in India. Link
May 15, 2025 (2mo ago)
Genie Worksheets is accepted to ACL 2025 (See you in Vienna!)
Mar 19, 2024 (1y ago)
Aligned with Prof. Monica Lam, excited to be working on conversational agents for the real world!
Jan 6, 2024 (1y ago)
I am rotating with Prof. Diyi Yang for the winter quarter (W '24) in the Social And Language Technologies (SALT) Lab!
Publications
2025
Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets
H. Joshi, S. Liu, J. Chen, L. Weighle, M.S. Lam • ACL 2025
2024
FLAME: A small language model for spreadsheet formulas
H. Joshi, A. Ebenezer, J. Cambronero, S. Gulwani, A. Kanade, V. Le, I. Radicek, G. Verbruggen • AAAI 2024
2023
Repair Is Nearly Generation: Multilingual Program Repair with LLMs
H. Joshi, J. Cambronero, S. Gulwani, A. Kanade, V. Le, I. Radicek, G. Verbruggen • AAAI 2023