Albert Yu Sun

Albert Sun

I'm a ML Research Engineer at Epiq AI Labs in New York City, NY. I'm currently building large-scale legal reasoning benchmarks for large language models. Previously, I worked on topics of differential privacy, ML interpretability, and AI safety.

Email: alsunyu@gmail.com Google Scholar: @albertyusun LinkedIn: @albertyusun Twitter: @albertyusun

Selected Publications

  • CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants
    Albert Yu Sun, Varun Nair, Elliot Schumacher, Anitha Kannan
    NAACL, 2024
    [Paper] [Dataset] [Patent]
    Patent: US Patent 12,259,952, 2025
  • Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?
    Albert Yu Sun, Eliott Zemour, Arushi Saxena, Udith Vaidyanathan, Eric Lin, Christian Lau, Vaikkunth Mugunthan
    arXiv, 2023
    [Paper]
  • Navigating progress: Enhancing public transit for more equitable communities via interpretable causal inference
    Gaurav Rajesh Parikh*, Jenny Huang*, Albert Sun*, Lesia Semenova*, Cynthia Rudin*
    Harvard Data Science Review, 2025
    [Paper]
    Also presented at: NeurIPS 2022 Causal Machine Learning for Real-World Impact
    🏆 Best Student Paper Award, 2022 American Statistical Association Data Challenge Expo Student Competition
  • Multi-Analyst Differential Privacy for Online Query Answering
    David Pujol, Albert Sun, Brandon Fain, Ashwin Machanavajjhala
    VLDB, 2022
    [Paper]
    Also presented at: ICML 2022 Theory and Practice of Differential Privacy Workshop

Research News

  • March 2024: My first-author paper, "CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants", was accepted to NAACL 2024! See you in New Mexico.
  • March 2023: I served as a reviewer for EMNLP 2023.
  • July 2023: We submitted our preprint "Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?" to Arxiv. This was my first project at DynamoFL, and we were first to analyze privacy leakage from OpenAI's fine-tuning API.

Previous Experiences

  • Epiq AI Labs - AI Research Engineer (2025-present)
  • Dynamo AI - ML Research Engineer II (2023-2025)
  • Curai Health - ML Research Intern (2023)
  • Microsoft Research - ML Research Intern (2022)
  • Vera Institute of Justice - Data Science Intern (2020-2021)
  • ACLU - Legal Intern (2020)