* denotes equal contribution.
Preprints
Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models.
Katie Matton, Rosalind W. Picard, John Guttag, Maggie Makar.
arXiv:2610.33904, 2026.
[arXiv]
MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering.
Robert Ness, Katie Matton, Hayden Helm, Sheng Zhang, Junaid Bajwa, Carey E. Priebe, Eric Horvitz.
arXiv:2406.06573, 2024.
[arXiv]
Conference and Journal Publications
Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression.
Katie Matton, Purvaja Balaji, Hamzeh Ghasemzadeh, Jameson C. Cooper, Daryush D. Mehta, Jarrad H. Van Stan, Robert E. Hillman, Rosalind Picard, John Guttag, S. Mazdak Abulnaga.
Machine Learning for Health (ML4H) 2025.
[pdf] [code]
Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations.
Katie Matton, Robert Ness, John Guttag, Emre Kıcıman.
ICLR 2025. Spotlight (top 3%).
[pdf]
Contrastive Learning of Electrodermal Activity Representations for Stress Detection.
Katie Matton*, Robert Lewis*, John Guttag, Rosalind Picard.
Conference on Health, Inference, and Learning (CHIL) 2023.
[pdf]
Understanding the Impact of COVID-19 on Online Mental Health Forums.
Laura Biester, Katie Matton, Janarthanan Rajendran, Emily Mower Provost, Rada Mihalcea.
ACM Transactions on Management Information Systems, 2021.
[pdf]
Into the Wild: Transitioning from Recognizing Mood in Clinical Interactions to Personal Conversations for Individuals with Bipolar Disorder.
Katie Matton, Melvin G. McInnis, Emily Mower Provost.
INTERSPEECH 2019. Oral presentation.
[pdf]
When to Intervene: Predicting Individual Outcomes for Rapid Intervention (PRIORI) Using Passively Collected Speech from Smartphone Conversations.
John Gideon, Katie Matton, Steve Anderau, Melvin G. McInnis, Emily Mower Provost.
Bipolar Disorders, 2020.
[arXiv preprint]
Workshops
A Removal Based Approach to Improve LLM Faithfulness at Test-Time.
Qinglan Luo, S M A Nahian, John Guttag, S. Mazdak Abulnaga, Katie Matton.
Workshop on Trustworthy AI for Good, NeurIPS 2026.
[arXiv]
Improving Domain Generalization in Contrastive Learning using Adaptive Temperature Control.
Katie Matton*, Robert Lewis*, Rosalind Picard, John Guttag.
Workshop on Self-Supervised Learning, NeurIPS 2023.
[pdf]
Invariance-Based Causal Estimation in the Presence of Concept Drift.
Katie Matton, John Guttag, Rosalind Picard.
Workshop on Causal Representation Learning, UAI 2022.
[pdf]
Quantifying the Effects of COVID-19 on Mental Health Support Forums.
Laura Biester*, Katie Matton*, Janarthanan Rajendran, Emily Mower Provost, Rada Mihalcea.
Workshop on NLP for COVID-19, EMNLP 2020. Oral presentation.
[pdf]