Hui Fen (Sarah) Tan
Google Scholar
LinkedIn
Github

I am a researcher interested in AI safety, causal inference, interpretability, and healthcare. Currently, I am a Principal Research Scientist at Salesforce. I also hold a Visiting Scientist appointment at Cornell University.

I received my PhD in Statistics from Cornell University, where I was advised by Giles Hooker and Martin Wells, with Thorsten Joachims and Rich Caruana on my committee. My dissertation was on the topic of interpretability of black-box AI models. Before graduate school, I studied at Berkeley and worked in public policy in NYC, including the health department and public hospitals system. I have worked at Facebook, UCSF, and Microsoft Research. I'm also interested in startups, stemming from my experience as part of the founding team at a NLP startup pre graduate school. From 2023 to 2026, I was President of Women in Machine Learning; I am currently on its Advisory Council.

You can reach me at ht395 AT cornell.edu.

• 3/26: Gave a guest lecture to UC Berkeley’s MBA/EWMBA 277 “Ethical AI Business Design” class.
• 1/26: Representing Salesforce on a Partnership in AI agents monitoring working group and AI safety steering committee.
• 12/25: Gave an invited talk at the Evaluating Evaluations Workshop, a NeurIPS 2025 satellite event.
• 8/25: Co-organizing 3rd edition of Regulatable ML workshop at NeurIPS 2025. Submit your paper!
• 8/24: Representing Salesforce on a US AI Safety Institute / Center for AI Standards and Innovation / NIST working group
• 5/24: Did a fireside chat in the University of Colorado Denver’s PUAD 6600 “AI for Public Sector Innovation” class.
• 1/23: I will be the Tutorial Chair for FAccT 2023.

For other news, click here.

Journal and Conference Papers

• Evaluating Cultural and Social Awareness of LLM Web Agents
  • H Qiu, AR Fabbri, D Agarwal, KH Huang, Tan, N Peng, CS Wu
  • NAACL 2025
  • Also appeared in: SoCal NLP Symposium 2024 and C3NLP 2025 Workshop
• Error Discovery By Clustering Influence Embeddings
  • F Wang, J Adebayo, Tan, D Garcia-Olano, N Kokhlikyan
  • NeurIPS 2023
  • Also appeared in: ICLR 2023 Pitfalls of limited data and computation for Trustworthy ML Workshop (Oral)
• Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?
  • Z Chen, Tan, U Chajewska, C Rudin, R Caruana
  • CHIL 2023
• Considerations When Learning Additive Explanations for Black-Box Models
  • Tan, G Hooker, P Koch, A Gordo, R Caruana
  • Machine Learning 2023
  • Also appeared in: NeurIPS 2018 Machine Learning for Health Workshop
• Interpretable Personalized Experimentation
  • H Wu, Tan, W Li, M Garrard, A Obeng, D Dimmery, S Singh, H Wang, D Jiang, E Bakshy
  • KDD 2022
  • Also appeared in: Conference on Digital Experimentation 2021 (Oral)
• How Interpretable and Trustworthy are GAMs?
  • CH Chang, Tan, B Lengerich, A Goldenberg, R Caruana
  • KDD 2021
• Do I Look Like a Criminal? Examining the Impact of Racial Information on Human Judgement
  • K Mallari, K Inkpen, P Johns, Tan, D Ramesh, E Kamar
  • CHI 2020
• Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable
  • Tan, M Soloviev, G Hooker, M Wells
  • ACM-IMS FODS 2020
  • Also appeared in: NIPS 2016 Interpretability Workshop
  • Code
• Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models
  • B Lengerich, Tan, CH Chang, G Hooker, R Caruana
  • AISTATS 2020
• Axiomatic Interpretability for Multiclass Additive Models
  • X Zhang, Tan, P Koch, Y Lou, U Chajewska, R Caruana
  • KDD 2019 (Oral)
  • Video
• Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation
  • Tan, R Caruana, G Hooker, Y Lou
  • AIES 2018 (Oral)
  • Also appeared in: NIPS 2017 Interpretability Symposium (Spotlight), NIPS 2017 Transparent Machine Learning in Safety Critical Environments Workshop (Spotlight)
  • Media coverage: MIT Technology Review, Politico, Futurism, WorkFlow
  • Code and data
• A Bayesian Evidence Synthesis Approach to Estimate Disease Prevalence in Hard-To-Reach Populations: Hepatitis C in New York City
  • Tan, S Makela, D Heller, K Konty, S Balter, T Zheng, J Stark
  • Epidemics 2018
  • Presented to NYC Health Commissioner. Talk at NDRI
  • Code
• “No Fracking Way!” Documentary Film, Discursive Opportunity, and Local Opposition against Hydraulic Fracturing in the United States, 2010 to 2013
  • I Vasi, E Walker, JS Johnson, Tan
  • American Sociological Review 2015
  • 2 Best Paper Awards from American Sociological Association’s CITAMS and CBSM sections
  • Media coverage: The Guardian, The Atlantic, Pacific Standard
  • Press releases: University of Iowa, Harmony Institute

Patents

• XForecast: Evaluating Natural Language Explanations for Time Series Forecasting
  • T Aksu, C Liu, A Saha, Tan, C Xiong, D Sahoo
  • Patent application

Preprints

• MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems
  • C Xu, Z Chen, J Zhang, F Lecue, A Kothari, Tan, W Guo, B Li
  • Under review
• ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems
  • R Bharathwaj, A Prabhakar, R Ram, A Kothari, Tan, H Wang, S Savarese
  • Under review
• The Observability Gap in Multi-Agent AI Systems
  • E Mibuari, M Srikumar, CR Leibowicz, Tan, B Blili-Hamelin, VX Nguyen, A Oueslati, A Sanka, XH Lu, J Stanley, KW Hall, K Klyman
  • Under review
• The Clinician’s Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
  • E LaRocco, Tan, A Subbaswamy, A Andrews, A Taylor, C Gaskin, C Agarwal
  • Under review
• Enduring Disparities in the Workplace: A Pilot Study in the AI Community
  • Y S Abdulsalam, S M Hall, A Quintero-Ossa, W Agnew, C Muntean, Tan, A Heady, S Thais, J Schrouff
  • Under review
• Generative Models, Humans, Predictive Models: Who Is Worse at High-Stakes Decision Making?
  • K Mallari, J Adebayo, K Inkpen, MT Wells, A Gordo, Tan
  • Under review
• MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases
  • R Murthy, L Yang, J Tan, T Awalgaonkar, Y Zhou, S Heinecke, S Desai, J Wu, R Xu, Tan, J Zhang, Z Liu, S Kokane, Z Liu, M Zhu, H Wang, C Xiong, S Savarese
  • Under review

For older publications and workshop papers, click here.

• Code for gradient boosted trees distance proposed in tree space prototypes paper
• R package surfin: (Statistical Inference for Random Forests)
• Data and code for distilling black-box risk scores paper

• Area Chair for NeurIPS 2025-2026, ICML 2026, FAccT 2023-2026, CHIL 2024-2026, ICLR 2027, Machine Learning for Health Symposium 2020-2023
• Senior Program Committee Member for AAAI 2027
• Reviewer for AISTATS, WWW, JAIR, Nature, Machine Learning, TMLR, TPAMI, TIST, Journal of Biomedical and Health Informatics