93 citations · 364 across the 27 of their papers we have counts for
5 papers · 1 filter
Invariant Language Modeling
Maxime Peyrard, Sarvjeet Singh Ghotra, Martin Josifoski +5
Large pretrained language models are critical components of modern NLP pipelines. Yet, they suffer from spurious correlations, poor out-of-domain generalization, and biases. Inspir…
Population-scale dietary interests during the COVID-19 pandemic
Kristina Gligoric, Arnaud Chiolero, Emre Kıcıman +2
The SARS-CoV-2 virus has altered people's lives around the world. Here we document population-wide shifts in dietary interests in 18 countries in 2020, as revealed through time ser…
DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions
Amit Sharma, Vasilis Syrgkanis, Cheng Zhang +1
Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and…
Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix
Ruocheng Guo, Pengchuan Zhang, Hao Liu +1
This work considers the out-of-distribution (OOD) prediction problem where (1)~the training data are from multiple domains and (2)~the test domain is unseen in the training. DNNs f…
Formation of Social Ties Influences Food Choice: A Campus-Wide Longitudinal Study
Kristina Gligorić, Ryen W. White, Emre Kıcıman +3
Nutrition is a key determinant of long-term health, and social influence has long been theorized to be a key determinant of nutrition. It has been difficult to quantify the postula…