5 papers
Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators
Anissa Alloula, Federico Licini, Ava Batchkala +1
LLMs-as-judges are the primary way to evaluate safety at scale. Despite their importance, LLM-judges themselves are rarely evaluated beyond human agreement in simple, static benchm…
When does Subgroup Balance Matter? Predicting Performance Sensitivity from Latent Separability
Anissa Alloula, Charles Jones, Zuzanna Wakefield-Skorniewska +2
Unequal representation of demographic groups in training data poses challenges to model generalisation across populations. Standard practice assumes that balancing subgroup represe…
Subgroups Matter for Robust Bias Mitigation
Anissa Alloula, Charles Jones, Ben Glocker +1
Despite the constant development of new bias mitigation methods for machine learning, no method consistently succeeds, and a fundamental question remains unanswered: when and why d…
On Biases in a UK Biobank-based Retinal Image Classification Model
Anissa Alloula, Rima Mustafa, Daniel R McGowan +1
Recent work has uncovered alarming disparities in the performance of machine learning models in healthcare. In this study, we explore whether such disparities are present in the UK…
Autopet Challenge 2023: nnUNet-based whole-body 3D PET-CT Tumour Segmentation
Anissa Alloula, Daniel R McGowan, Bartłomiej W. Papież
Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) combined with Computed Tomography (CT) scans are critical in oncology to the identification of solid tumours and the monit…