2 papers
cs.CY2025
Arti-"fickle" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences
Lisa P. Argyle, Ethan C. Busby, Joshua R. Gubler +3
Generative large language models (LLMs) are incredibly useful, versatile, and promising tools. However, they will be of most use to political and social science researchers when th…
cs.LG2025
Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning
Jeffrey Olmo, Jared Wilson, Max Forsey +3
Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal acti…