← Search

Szilvia Ujváry

2 accepted papers

2024

Position: Understanding LLMs Requires More Than Statistical Generalization

ICML 2024spotlight

The last decade has seen blossoming research in deep learning theory attempting to answer, ``Why does deep learning generalize?" A powerful shift in perspective precipitated this progress: the study of overparametrized models in the interpolation regime. In this paper, we argue that another perspect…

2024

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts

NeurIPS 2024spotlight

LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attributed to the Transformer architecture, our systematic understanding is limited. In complex real-world data sets, even defin…

Cited by 2SourcePDFScholar