activity
20212026
most citedHow can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations

90 citations · 108 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings

Inês Oliveira e Silva, Sérgio Jesus, Iker Perez +4

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deploy…

cs.LG2024

Fair-OBNC: Correcting Label Noise for Fairer Datasets

Inês Oliveira e Silva, Sérgio Jesus, Hugo Ferreira +4

Data used by automated decision-making systems, such as Machine Learning models, often reflects discriminatory behavior that occurred in the past. These biases in the training data…

cs.LG20241 cited

Aequitas Flow: Streamlining Fair ML Experimentation

Sérgio Jesus, Pedro Saleiro, Inês Oliveira e Silva +5

Aequitas Flow is an open-source framework and toolkit for end-to-end Fair Machine Learning (ML) experimentation, and benchmarking in Python. This package fills integration gaps tha…

cs.LG2024

Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints

Jean V. Alves, Diogo Leitão, Sérgio Jesus +5

Learning to defer (L2D) aims to improve human-AI collaboration systems by learning how to defer decisions to humans when they are more likely to be correct than an ML classifier. E…

cs.LG2023

FiFAR: A Fraud Detection Dataset for Learning to Defer

Jean V. Alves, Diogo Leitão, Sérgio Jesus +4

Public dataset limitations have significantly hindered the development and benchmarking of learning to defer (L2D) algorithms, which aim to optimally combine human and AI capabilit…

cs.LG2023

A Case Study on Designing Evaluations of ML Explanations with Simulated User Studies

Ada Martin, Valerie Chen, Sérgio Jesus +1

When conducting user studies to ascertain the usefulness of model explanations in aiding human decision-making, it is important to use real-world use cases, data, and users. Howeve…