Evaluating and mitigating discrimination in language model decisions

A Tamkin, A Askell, L Lovitt, E Durmus… - ar** A Voting Mechanism for Blockchain-based AI Alignment
A Neulinger, L Sparer, M Roshanaei… - 2024 6th International …, 2024 - ieeexplore.ieee.org
This paper proposes a novel anonymous voting mechanism for Artificial Intelligence (AI)
alignment rules and conducts an associated simulation. The aim is to provide a voting …

[PDF][PDF] Image-Conditioned Autocorrection in Medical Reporting

AC Asiimwe, D Surís, P Rajpurkar, C Vondrick - 2024 - raw.githubusercontent.com
In medical reporting, the accuracy of radiological reports, whether generated by humans or
machine learning algorithms, is critical. We tackle a new task in this paper …