Albert-Laszlo Barabasi — accepted AI-conference papers

2025

Unequal Scientific Recognition in the Age of LLMs

Yixuan Liu, Abel Elekes, Jianglin Lu, Rodrigo Dorantes-Gilardi, Albert-Laszlo Barabasi

EMNLP 2025

Large language models (LLMs) are reshaping how scientific knowledge is accessed and represented. This study evaluates the extent to which popular and frontier LLMs including GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro recognize scientists, benchmarking their outputs against OpenAlex and Wikipedia.

Cited by 0 Source ↗PDF ↗Scholar ↗

2019

Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

Nima Dehmamy, Albert-Laszlo Barabasi, Rose Yu

NeurIPS 2019poster

To deepen our understanding of graph neural networks, we investigate the representation power of Graph Convolutional Networks (GCN) through the looking glass of graph moments, a key property of graph topology encoding path of various lengths. We find that GCNs are rather restrictive in learning gra…

Cited by 177 Source ↗PDF ↗code ↗Scholar ↗