5 papers
Simplifying the Modeling of Arbitrary Conditionals in Natural Language
Yinhan Lu, Eric Elmoznino, Léo Gagnon +3
Causal Transformers model sequences through an autoregressive factorization of the joint distribution, which enables efficient left-to-right decoding and conditional likelihood com…
A Compression Perspective on Simplicity Bias
Tom Marty, Eric Elmoznino, Leo Gagnon +5
Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through t…
Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective
Leo Gagnon, Eric Elmoznino, Sarthak Mittal +4
The rapid adaptation ability of auto-regressive foundation models is often attributed to the diversity of their pre-training data. This is because, from a Bayesian standpoint, mini…
In-context learning and Occam's razor
Eric Elmoznino, Tom Marty, Tejas Kasetty +5
A central goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without further assumpt…
Evaluating Interventional Reasoning Capabilities of Large Language Models
Tejas Kasetty, Divyat Mahajan, Gintare Karolina Dziugaite +2
Numerous decision-making tasks require estimating causal effects under interventions on different parts of a system. As practitioners consider using large language models (LLMs) to…