Scholar
Reshabh K Sharma
Google Scholar ID: MEJGZWMAAAAJ
University of Washington
Citations & Impact
Citations
64
H-index
4
i10-index
3
Publications
5
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Published 'PromptPex: Automatic Test Generation for Language Model Prompts' as an arXiv preprint (2025).
- Co-authored blog post 'Testing AI Software Isn't Like Testing Plain Old Software'.
- Co-wrote 'Prompts are Programs'.
- Released 'SPML: A DSL for Defending Language Models Against Prompt Attacks' as an arXiv preprint (2024).
- Created the SPML Prompt Injection Dataset, which has been downloaded over 5,000 times and is available on Hugging Face and the project page.
- Published 'Defending Language Models Against Image-Based Prompt Attacks via User-Provided Specifications' at IEEE S&P (2024).
Research Experience
- Works at the intersection of Programming Languages and Large Language Models, researching how to improve the reliability and security of LLM-based software through infrastructure and tools.
Education
- Paul G. Allen School of Computer Science & Engineering, University of Washington, advised by Professor Dan Grossman.
Background
- PhD student with research interests in Programming Languages (PL) and Large Language Models (LLMs), focusing on the development of infrastructure and tools to improve the reliability, security, and maintainability of LLM-based software.
