4 papers
Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making
David Wingate, Sheryl Carty, Joshua Coates +13
As large language models become a default source of guidance on personal, moral, and existential questions, it matters whether they draw on the religious frameworks that have histo…
Language models struggle with compartmentalization
Thomas Vincent Howe, David Wingate
In the training data used by large language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear in English and Swahili; many…
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…
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…