When building a test set for binary classification from noisy label, how many labels to collect per data point? Surprisingly under a simple budget constraint, the answer is a single label.
Florian E. Dorner, Moritz Hardt
Workshop on Navigating and Addressing Data Problems for Foundation Models (at ICLR 2024)
We show how to use peer-prediction mechanisms to prevent rational clients from adversarially manipulating updates in federated learning.
Florian E. Dorner, Nikola Konstantinov, Georgi Pashaliev, Martin Vechev
NeurIPS 2023
Language models’ answers to personality tests markedly deviate from typical human responses.
Florian E. Dorner, Tom Sühr, Samira Samadi, Augustin Kelava (Equal contribution)
Socially Responsible Language Modelling Research Workshop (at NeurIPS 2023)
We use LLMs and human to generate valid constraints for individual fairness in text classification.
Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, and Martin Vechev
ICLR 2023 (Top 25% Spotlight)
A survey on experts’ opinions on forecasting AI progress.
Ross Gruetzemacher, Florian E. Dorner, Niko Bernaola-Alvarez, Charlie Giattino, David Manheim
Technological Forecasting and Social Change 170, 120909 (2021)
How realistic is the prospect of pricing algorithms learning to collude?
Florian E. Dorner
arxiv preprint
How has sample efficiency in deep reinforcement learning improved over time?
Florian E. Dorner
arxiv preprint