Valerie Chen

profile photo

I'm a fourth year Machine Learning PhD student at Carnegie Mellon University advised by Ameet Talwalkar and my PhD is supported by the NSF Graduate Research Fellowship. I previously interned at Microsoft Research in the FATE (Fairness, Accountability, Transparency, and Ethics of AI) group with Q. Vera Liao and Jennifer Wortman Vaughan. I completed my BS in Computer Science at Yale University, where I previously worked with Zhong Shao and Abhinav Gupta. I have also spent time at IBM Research and the Naval Research Laboratory.

Email / Google Scholar / Twitter

Current research interests

My research focuses on building tools and theory to improve human-AI interactions in real-world contexts, more recently focusing on human interactions with LLMs. Below are selected work on three topics that I am actively working on (full list here).

Understanding human-AI interactions

On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods
Kasun Amarasinghe, Kit Rodolfa, Sergio Jesus, Valerie Chen, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro, Ameet Talwalkar, Rayid Ghani
AAAI (Special Track on Safe, Robust and Responsible AI), 2024

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal
CSCW, 2023

Assisting Human Decisions in Document Matching
Joon Sik Kim, Valerie Chen, Danish Pruthi, Nihar Shah, Ameet Talwalkar
TMLR, 2023

Interpretable Machine Learning: Moving From Mythos to Diagnostics
Valerie Chen*, Jeffrey Li*, Joon Sik Kim**, Gregory Plumb**, Ameet Talwalkar
Communications of ACM, 2022

Improving human-AI interaction by incorporating user {expertise, preference, prior}

FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Matthew Barker, Emma Kallina, Dhananjay Ashok, Katherine Collins, Ashley Casovan, Adrian Weller, Ameet Talwalkar, Valerie Chen*, Umang Bhatt*
EAAMO, 2023

Learning Personalized Decision Support Policies
Umang Bhatt*, Valerie Chen*, Katie Collins, Parameswaran Kamalaruban, Emma Kallina, Adrian Weller, Ameet Talwalkar
Preprint

Perspectives on Incorporating Expert Feedback into Model Updates
Valerie Chen*, Umang Bhatt*, Hoda Heidari, Adrian Weller, Ameet Talwalkar
Patterns, 2023

Bayesian Persuasion for Algorithmic Recourse
Keegan Harris, Valerie Chen, Joon Sik Kim, Ameet Talwalkar, Hoda Heidari, Steven Wu
NeurIPS, 2022

Evaluating human-AI interaction by simulating human behaviors

Simulating Iterative Human-AI Interaction in Programming with LLMs
Hussein Mozannar*, Valerie Chen*, Dennis Wei, Prasanna Sattigeri, Manish Nagireddy, Subhro Das, Ameet Talwalkar, David Sontag
Neurips Workshop on Instruction Tuning and Instruction Following, 2023

Do LLMs exhibit human-like response biases? A case study in survey design
Lindia Tjuatja*, Valerie Chen*, Sherry Tongshuang Wu, Ameet Talwalkar, Graham Neubig
CMU LTI Student Research Symposium, 2023 (Best Preliminary Paper Award)

A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies
Ada Martin, Valerie Chen, Sergio Jesus, Pedro Saleiro
ICLR Workshop on Trustworthy ML, 2023

Use-Case-Grounded Simulations for Explanation Evaluation
Valerie Chen, Nari Johnson, Nicholay Topin*, Gregory Plumb*, Ameet Talwalkar
NeurIPS, 2022

Important non-research things


DEI Course at CMU ( check out the course website )

Yale Women's Leadership Initiative (support remembering 50 at Yale here )

SheCode at Yale ( org website)

Computation and Society at Yale ( yalies should get involved here )