Adam Stein

About

I'm a fourth year PhD student at the University of Pennsylvania advised by Professor Mayur Naik and Professor Eric Wong. Previously, I attended UCLA where I recieved my BS in CS in 2020. My research is supported by the NSF Graduate Research Fellowship Program.

I'm broadly interested in the fields of programming languages and machine learning, and I'm particularly interested in developing methods for interpreting and debugging machine learning models to improve their reliability and trustworthiness. In particular, I'm working on the following problems:

• What concepts has my model learned? Interpreting and evaluating the capabilities of deep learning models.
• How do I find and fix failures in my model? Building a language, TorchQL, for debugging deep learning models.
• What changed in my data distribution? Developing methods to find usable and robust explanations of distribution shift.

Pre-Prints

• Neuro-Symbolic Programming in the Age of Foundation Models: Pitfalls and Opportunities
  Pre-print, 2025
  Adam Stein, Aaditya Naik, Neelay Velingker, Mayur Naik, Eric Wong
• Where's the Bug? Attention Probing for Scalable Fault Localization
  arXiv Pre-print, 2025
  Adam Stein*, Arthur Wayne*, Aaditya Naik, Mayur Naik, Eric Wong
• Rectifying Group Irregularities in Explanations for Distribution Shift [code]
  arXiv Pre-print, 2023
  Adam Stein, Yinjun Wu, Eric Wong, Mayur Naik

Peer-Reviewed Papers

• Towards Style Alignment in Cross-Cultural Translation
  ACL 2025
  Shreya Havaldar*, Adam Stein*, Eric Wong, Lyle Ungar
• Towards Compositionality in Concept Learning [blog] [code]
  ICML 2024
  Adam Stein, Aaditya Naik, Yinjun Wu, Mayur Naik, Eric Wong
• TorchQL: A Programming Framework for Integrity Constraints in Machine Learning [code]
  OOPSLA 2024
  Aaditya Naik, Adam Stein, Yinjun Wu, Eric Wong, Mayur Naik
• Relational Query Synthesis ⨝ Decision Tree Learning
  VLDB 2024
  Aaditya Naik, Aalok Thakkar, Adam Stein, Mayur Naik, Rajeev Alur
• Faithful Chain-of-Thought Reasoning [blog] [code]
  AACL 2024 Area Chair Award
  Qing Lyu*, Shreya Havaldar*, Adam Stein*, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, Chris Callison-Burch
• TopEx: Topic-based Explanations for Model Comparison
  ICLR (Tiny Papers Track) 2023
  Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar
• Learning to Select Pivotal Samples for Meta Re-weighting [code]
  AAAI 2023 Oral Presentation
  Yinjun Wu, Adam Stein, Jacob Gardner, Mayur Naik
• Some Problems with Properties: A Study on Property-Based Testing in Industry
  HATRA @ SPLASH 2022
  Harrison Goldstein, Joseph W. Cutler, Adam Stein, Benjamin C. Pierce, Andrew Head

Projects

• Automatic Detection of Hybrid Human-Machine Text Boundaries
  CIS 520 Course Project, 2021
  Joseph W. Cutler*, Liam Dugan*, Shreya Havaldar*, Adam Stein*
• Weighted Contrastive Learning for Scene Graph Generation
  2021 Manuscript
  Joint work with Yinjun Wu and Adam Stein