1 citations · 1 across the 4 of their papers we have counts for
3 papers
Multicalibration for Confidence Scoring in LLMs
Gianluca Detommaso, Martin Bertran, Riccardo Fogliato +1
This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks…
Federated Fairness without Access to Sensitive Groups
Afroditi Papadaki, Natalia Martinez, Martin Bertran +2
Current approaches to group fairness in federated learning assume the existence of predefined and labeled sensitive groups during training. However, due to factors ranging from eme…
Distributionally Robust Group Backwards Compatibility
Martin Bertran, Natalia Martinez, Alex Oesterling +1
Machine learning models are updated as new data is acquired or new architectures are developed. These updates usually increase model performance, but may introduce backward compati…