Research Assistant
About Me
I am a PhD candidate in Software Engineering at UC Irvine, working with Cristina Videira Lopes on AI for reliable software engineering. My work spans LLM memorization and hallucination detection, retrieval-augmented generation (RAG), verified program synthesis with Dafny, and query-adaptive fusion methods for production search ranking.
I received a B.S. in Agronomy and Computer Science at Iowa State University. I worked as an undergraduate research assistant at Laboratory for Software Design with Hridesh Rajan and Robert Dyer on an ultra-large data mining project.
Research Interests
- LLM Memorization & Hallucination Detection
- Retrieval-Augmented Generation (RAG)
- Verified Program Synthesis
- Information Retrieval & Search Ranking
Education
- Ph.D. in Software Engineering
University of California, Irvine · current - M.S. in Software Engineering
University of California, Irvine · 2026 - B.S. in Agronomy, Computer Science
Iowa State University · 2022
Experience
Applied Scientist Intern
Applied Scientist Intern
Software Engineer Intern
Research Assistant
Publications
Query-adaptive WRRF methods for production search retrieval, showing optimal fusion weights form intervals rather than points and explaining RRF's near-optimality for a large share of queries.
An agentic system that iteratively synthesizes and refines formal specifications, going beyond verifier acceptance to ensure genuine correctness and completeness.
Extracting full books from Llama models via prefix prompting, and showing that instruction-tuning can undo alignment's memorization mitigations.
A RAG-based conversational assistant for Congenital Diaphragmatic Hernia questions, with accuracy improving substantially after knowledge-base expansion.
RAGMan is an LLM-powered tutoring system that can support a variety of course-specific and homework-specific AI tutors.
LLM shows “great promise” in code synthesis. Can LLM keep "the promise" to ensure that its synthesis code is formally correct?
Evaluating ChatGPT against prior automated approaches for commit message generation, finding it substantially outperforms methods trained specifically on commit data.
The research focuses on enhancing the quality of commit messages in collaborative software development by introducing specific requirements in the "what" and "why" parts through modifications to the GitHub Desktop application, demonstrating improved informativeness, clearness, and length in commit messages among students.
Honors & Awards
University of California, Irvine
- Beall Applied Innovation's Graduate Innovation Fellowship — $5,000 (2024)
- I-Corps Program — $5,000 (2024)
- Beall Applied Innovation's Proof-of-Product Grant — $48,000 (2024)
- ESEC/FSE Conference Travel Fund — $2,450 (2023)
- New Ph.D. Student Fellowship — $2,500 (2022)
Iowa State University
- Robert and Cecile Mitchell Scholarship — $2,650 (2021)
- International Incentive Scholarship — $1,500 (2021)
- Global Scholars Award for Undergraduate Retention — $500 (2021)
- International Incentive Scholarship — $1,500 (2020)
- Dean's List Honors (10 times)
Mentoring
Undergraduate Student, University of Waterloo (Summer 2026 -- present)
Undergraduate Student, UCI (Winter 2024 -- Spring 2025)
Undergraduate Student, UCI (Winter 2024 -- Spring 2025)
Undergraduate Student, UCI (Winter 2024 -- Spring 2025)
Andy Anh-Huy Tonthat
Undergraduate Student, UCI (Summer 2024)
Avery Zhuang
Undergraduate Student, UCI (Summer 2024)
Undergraduate Student, UCI (Summer 2024)
Undergraduate Student, UCI (Summer 2024)
Undergraduate Student, UCI (Summer 2024)