6 papers · 1 filter
Distributed Sparse Interventions in Language Models
Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1
Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and se…
Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
Lorenz Linhardt, Tom Neuhäuser, Lenka Tětková +1
Small and mid-sized generative language models have gained increasing attention. Their size and availability make them amenable to being analyzed at a behavioral as well as a repre…
Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
Teresa Dorszewski, Lenka Tětková, Lorenz Linhardt +1
Understanding how neural networks align with human cognitive processes is a crucial step toward developing more interpretable and reliable AI systems. Motivated by theories of huma…
An Analysis of Human Alignment of Latent Diffusion Models
Lorenz Linhardt, Marco Morik, Sidney Bender +1
Diffusion models, trained on large amounts of data, showed remarkable performance for image synthesis. They have high error consistency with humans and low texture bias when used f…
Learning Counterfactual Representations for Estimating Individual Dose-Response Curves
Patrick Schwab, Lorenz Linhardt, Stefan Bauer +2
Estimating what would be an individual's potential response to varying levels of exposure to a treatment is of high practical relevance for several important fields, such as health…
Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks
Patrick Schwab, Lorenz Linhardt, Walter Karlen
Learning representations for counterfactual inference from observational data is of high practical relevance for many domains, such as healthcare, public policy and economics. Coun…