Avishree Khare

Hi! I am a second-year PhD student in Computer Science at the University of Pennsylvania, where I am fortunate to be advised by Prof. Rajeev Alur.

I am broadly interested in research topics at the intersection of Machine Learning and Formal Methods. My research currently aims to:

Evaluate the formal reasoning capabilities of Large Language Models (LLMs)
Augment LLMs with formal techniques to build more trustworthy systems

Prior to joining Penn, I was a Research Fellow with the PROSE group at Microsoft . I also spent a year as a Software Engineer at Google. Before that, I graduated with a B.E in Computer Science from BITS Pilani Goa, India.

In my spare time, I enjoy running, (pen) sketching and baking bread!

news

Jan 2025	Logicbreaks has been accepted to ICLR 2025! Check out the paper and blogpost!
Dec 2024	Understanding the Effectiveness of LLMs in Detecting Security Vulnerabilities has been accepted to ICST 2025!
Nov 2024	We will be presenting Logicbreaks at three NeurIPS 2024 workshops: AdvML-Frontiers, SciForDL and SATA!
Dec 2023	We will be presenting GrACE at FSE 2023!

publications

Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference

Anton Xue^*, Avishree Khare^*, Rajeev Alur, Surbhi Goel, and Eric Wong

In The Thirteenth International Conference on Learning Representations (ICLR), 2025
Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities

Avishree Khare^*, Saikat Dutta^*, Ziyang Li, Alaia Solko-Breslin, Mayur Naik, and Rajeev Alur

In Proceedings of the 2025 IEEE Conference on Software Testing, Validation and Verification (ICST), 2025
Grace: Language models meet code edits

Priyanshu Gupta^*, Avishree Khare^*, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, and Ashish Tiwari

In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE), 2023

^*equal contribution