51 citations · 112 across the 28 of their papers we have counts for
9 papers · 1 filter
Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting
Siyu Zhou, Jialin Ouyang, Fan Xia +8
Continuous monitoring of generative AI systems requires detecting distribution shifts in the unstructured data they ingest and generate. Existing monitoring methods typically contr…
Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control
Will Y. Zou, Jean Feng, Alexandre Kalimouttou +3
Reinforcement learning (RL) applications in Clinical Decision Support Systems (CDSS) frequently encounter skepticism because models may recommend inoperable dosing decisions. We pr…
Reflections from Research Roundtables at the Conference on Health, Inference, and Learning (CHIL) 2025
Emily Alsentzer, Marie-Laure Charpignon, Bill Chen +90
The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025…
"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift
Harvineet Singh, Fan Xia, Alexej Gossmann +3
Machine learning (ML) models frequently experience performance degradation when deployed in new contexts. Such degradation is rarely uniform: some subgroups may suffer large perfor…
LLMs Judging LLMs: A Simplex Perspective
Patrick Vossler, Fan Xia, Yifan Mai +2
Given the challenge of automatically evaluating free-form outputs from large language models (LLMs), an increasingly common solution is to use LLMs themselves as the judging mechan…
Bayesian Concept Bottleneck Models with LLM Priors
Jean Feng, Avni Kothari, Luke Zier +2
Concept Bottleneck Models (CBMs) have been proposed as a compromise between white-box and black-box models, aiming to achieve interpretability without sacrificing accuracy. The sta…
A hierarchical decomposition for explaining ML performance discrepancies
Jean Feng, Harvineet Singh, Fan Xia +2
Machine learning (ML) algorithms can often differ in performance across domains. Understanding their performance differs is crucial for determining what types of int…
Designing monitoring strategies for deployed machine learning algorithms: navigating performativity through a causal lens
Jean Feng, Adarsh Subbaswamy, Alexej Gossmann +7
After a machine learning (ML)-based system is deployed, monitoring its performance is important to ensure the safety and effectiveness of the algorithm over time. When an ML algori…
Is this model reliable for everyone? Testing for strong calibration
Jean Feng, Alexej Gossmann, Romain Pirracchio +3
In a well-calibrated risk prediction model, the average predicted probability is close to the true event rate for any given subgroup. Such models are reliable across heterogeneous…