Victoria Lin

Hello! I am a PhD student in the Department of Statistics and the Machine Learning Department at Carnegie Mellon University, where I am advised by Louis-Philippe Morency and Eli Ben-Michael. I am broadly interested in problems at the intersection of causal inference and machine learning, particularly in natural language settings. My work is supported by a Meta Research PhD Fellowship.

I'm currently a Student Researcher at Google DeepMind with Alexander D'Amour and have interned at Microsoft Research Cambridge and Microsoft Research Redmond. Before my PhD, I was a master's student in CMU's Language Technologies Institute, where I worked on multimodal machine learning and affective computing (also with LP Morency and with Jeffrey Girard). I obtained my AB in Statistics and Molecular & Cellular Biology from Harvard University, then spent a wonderful year as a researcher with Miguel Hernán in the Program for Causal Inference (now CAUSALab) at the Harvard School of Public Health.

I am on the 2026 job market. If you'd like to chat, please feel free to reach out at victoria(at)stat(dot)cmu(dot)edu.

Publications
* denotes equal contribution

Conferences

Omitted Variable Bias in Language Models Under Distribution Shift
Victoria Lin, Louis-Philippe Morency, Eli Ben-Michael
ICML 2026

Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
Victoria Lin, Xinnuo Xu, Rachel Lawrence, Risa Ueno, Amit Sharma, Javier Gonzalez, Niranjani Prasad
ICLR 2026 Workshop on Logical Reasoning of Large Language Models

Isolated Causal Effects of Natural Language [code]
Victoria Lin, Louis-Philippe Morency, Eli Ben-Michael
ICML 2025

Optimizing Language Models for Human Preferences is a Causal Inference Problem [code]
Victoria Lin, Eli Ben-Michael, Louis-Philippe Morency
UAI 2024

Text-Transport: Toward Learning Causal Effects of Natural Language [code]
Victoria Lin, Louis-Philippe Morency, Eli Ben-Michael
EMNLP 2023

Counterfactual Augmentation for Multimodal Learning Under Presentation Bias [code]
Victoria Lin, Louis-Philippe Morency, Dimitrios Dimitriadis, Srinagesh Sharma
EMNLP Findings 2023

SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations [code]
Victoria Lin, Louis-Philippe Morency
ACL Findings 2023

SeedBERT: Recovering Annotator Rating Distributions from an Aggregated Label
Aneesha Sampath, Victoria Lin, Louis-Philippe Morency
AAAI 2023 Workshop on Uncertainty Reasoning and Quantification in Decision Making

Toward Multimodal Modeling of Emotional Expressiveness [code]
Victoria Lin*, Jeffrey Girard*, Michael Sayette, Louis-Philippe Morency
ICMI 2020 (Best Paper nominee)

Context-Dependent Models for Predicting and Characterizing Facial Expressiveness
Victoria Lin, Jeffrey Girard, Louis-Philippe Morency
AAAI 2020 Workshop on Affective Content Analysis (Best Paper Award)

Journals

gfoRmula: An R package for estimating the effects of sustained treatment strategies via the parametric g-formula [code][software]
Sean McGrath*, Victoria Lin*, Zilu Zhang, Lucia Petito, Roger Logan, Miguel Hernán, Jessica Young
Patterns Volume 1, Issue 3 (2020)

Enhancing GABA signaling during middle adulthood prevents age-dependent GABAergic interneuron decline and learning and memory deficits in ApoE4 mice
Leslie Tong, Seo Yeon Yoon, Yaisa Andrews-Zwilling, Alyssa Yang, Victoria Lin, Hanci Lei, Yadong Huang
Journal of Neuroscience Volume 36, Issue 7 (2016)