Sarah Fakhoury

Sarah Fakhoury sfakhoury@microsoft.com
CV / GitHub / Google Scholar

Welcome

I am a postdoctoral researcher in the Research in Software Engineering (RiSE) group at Microsoft Research in Redmond.

My research centers around ways to improve the design and evaluation of software development tools to optimize the cognitive effort of programmers. I am currently interested in leveraging formal methods as a mechanism to provide end-user trust and verifiability of AI-assisted programming tools. My approach to research is largely interdisciplinary, fusing: formal methods, empirical software engineering, machine learning, and human-computer interaction

In 2022, I completed my Ph.D. in Computer Science from Washington State University, advised by Dr. Venera Arnaoudova.

Latest News

Apr 2024 Check out our latest paper: 3DGen: AI-Assisted Generation of Provably Correct Binary Format Parsers
Apr 2024 "Formalizing Natural Language Intent into Program Specifications via Large Language Models" accepted to FSE 2024!
Apr 2024 Talk on "Leveraging Formal Methods for Trustworthy AI-Assisted Software Development" at University of Michigan
Oct 2023 Check out our latest paper: Formalizing Natural Language Intent into Program Specifications via Large Language Models
Oct 2023 Check out our latest paper: Interactive Code Generation via Test-Driven User-Intent Formalization
Aug 2023 Muslims in ML @ NeurIPS 2023 -- CFP now open!
I am happy to be co-organizing the Muslims in ML workshop at NeurIPS 2023. Consider submitting your work!
Apr 2023 Check out our latest paper: Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions
2023 Happy to serve on the PC for ESEC/FSE (‘23, ‘24), ICSE (‘24), ASE(‘23), DL4Code ICLR(‘23)
Aug 2022 In August 2022, I will be joining the RiSE team at Microsoft Research!
Jun 2022 Our paper "Program Merge Conflict Resolution via Neural Transformers" has been accepted to ESEC/FSE 2022!
May 2022 Invited to the Eye Movements in Programming (EMIP 2022) panel on "Practical Implications of EMIP Research on Software Engineering and CS Education". EMIP will be held on May 18, 2022 and is co-located with ICSE!
Jan 2022 Invited to the Schloss Dagstuhl Seminar on Foundations for a New Perspective of Understanding Programming October 3 - 7.
Nov 2021 Excited to be serving on the organzing committee for ICPC 2022 as Publicity Chair and Tool Track PC member, and ETRA 2022 as Virtualization chair. Consider submitting!

Preprints

3DGen: AI-Assisted Generation of Provably Correct Binary Format Parsers
Sarah Fakhoury, Markus Kuppe, Shuvendu K. Lahiri, Tahina Ramananandro and Nikhil Swamy. arxiv. 2024.
Preprint

Formalizing Natural Language Intent into Program Specifications via Large Language Models
Madeline Endres, Sarah Fakhoury, Saikat Chakraborty, Shuvendu K. Lahiri. arxiv. 2023.
Preprint

Publications

Exploring the Effectiveness of LLM based Test-driven Interactive Code Generation: User Study and Empirical Evaluation
Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Madanlal Musuvathi, Shuvendu Lahiri. ICSE-Companion. 2024.
Paper

Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions
Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Madanlal Musuvathi, Shuvendu Lahiri. ICSE-Companion. 2024.
Paper

Ranking LLM-Generated Loop Invariants for Program Verification
Saikat Chakraborty, Shuvendu K. Lahiri, Sarah Fakhoury, Madanlal Musuvathi, Akash Lal, Aseem Rastogi, Aditya Senthilnathan, Rahul Sharma, Nikhil Swamy. EMNLP. 2023.
Paper

Models, Metrics, and Minds: Empirical Perspectives on Developer Productivity
Sarah Fakhoury PhD Thesis, Washington State University, 2022.
Paper

Program Merge Conflict Resolution via Neural Transformers
Alexey Svyatkovskiy, Sarah Fakhoury, Negar Ghorbani, Todd Mytkowicz, Elizabeth Dinella, Christian Bird, Jinu Jang, Neel Sundaresan, Shuvendu Lahiri.
ESEC/FSE 2022
Paper

Reassessing Automatic Evaluation Metrics for Code Summarization Tasks
Devjeet Roy, Sarah Fakhoury, Venera Arnaoudova.
ESEC/FSE 2021
Paper

Gazel: Supporting Source Code Edits in Eye-Tracking Studies
Sarah Fakhoury, Devjeet Roy, Harry Pines, Tyler Cleveland, Cole Person, Venera Arnaoudova, Bonita Sharif, Jonathan Maletic
ICSE 2021
Paper / Demo

A Model to Detect Readability Improvements in Incremental Changes
Devjeet Roy, Sarah Fakhoury, John Lee, Venera Arnaoudova
ICPC 2020
Paper

VITALSE: Visualizing Eye Tracking and Biometric Data
Devjeet Roy, Sarah Fakhoury, Venera Arnaoudova
ICSE 2020
Paper / Demo

Measuring the Impact of Lexical and Structural Inconsistencies on Developers’ Cognitive Load During Bug Localization
Sarah Fakhoury, Devjeet Roy, Yuzhan Ma, Venera Arnaoudova, Olusola Adesope
EMSE 2019
Paper

Measuring the Impact of Lexical and Structural Inconsistencies on Developers’ Cognitive Load During Bug Localization
Sarah Fakhoury, Devjeet Roy, Yuzhan Ma, Venera Arnaoudova, Olusola Adesope
EMSE 2019
Paper

Improving Source Code Readability: Theory and Practice
Sarah Fakhoury, Devjeet Roy, Adnan Hassan, Venera Arnaoudova
ICPC 2019
Paper

Moving Towards Objective Measures of Program Comprehension
Sarah Fakhoury
ESEC/FSE 2018
Paper

The Effect of Poor Source Code Lexicon and Readability on Developers' Cognitive Load
Sarah Fakhoury, Yuzhan Ma, Venera Arnaoudova, Olusola Adesope
ICPC 2018
ACM/SIGGSOFT Distinguished Paper Award
Paper

Automatic Classification of Software Artifacts in Open-Source Applications
Yuzhan Ma, Sarah Fakhoury, Michael Christensen, Venera Arnaoudova, Waleed Zogaan, Mehdi Mirakhorli
MSR 2018
Paper