9 papers
Efficient bias mitigation in T2I diffusion models using Concept Graphs
Mansi, Avinash Kori, Francesco Leofante
Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene only at the text encoder or pr…
Attribution-based Explanations for Markov Decision Processes
Paul Kobialka, Andrea Pferscher, Francesco Leofante +3
Attribution techniques explain the outcome of an AI model by assigning a numerical score to its inputs. So far, these techniques have mainly focused on attributing importance to st…
Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders
Junqi Jiang, Francesco Leofante, Antonio Rago +1
Counterfactual explanations (CEs) provide recourse recommendations for individuals affected by algorithmic decisions. A key challenge is generating CEs that are robust against vari…
Representation Consistency for Accurate and Coherent LLM Answer Aggregation
Junqi Jiang, Tom Bewley, Salim I. Amoukou +4
Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate m…
Counterfactual Scenarios for Automated Planning
Nicola Gigante, Francesco Leofante, Andrea Micheli
Counterfactual Explanations (CEs) are a powerful technique used to explain Machine Learning models by showing how the input to a model should be minimally changed for the model to…
Argumentative Ensembling for Robust Recourse under Model Multiplicity
Junqi Jiang, Antonio Rago, Francesco Leofante +1
In machine learning, it is common to obtain multiple equally performing models for the same prediction task, e.g., when training neural networks with different random seeds. Model…