3 papers
cs.LG2024
Are Logistic Models Really Interpretable?
Danial Dervovic, Freddy Lécué, Nicolás Marchesotti +1
The demand for open and trustworthy AI models points towards widespread publishing of model weights. Consumers of these model weights must be able to act accordingly with the infor…
cs.LG2024
Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
Sanjay Kariyappa, Freddy Lécué, Saumitra Mishra +3
This paper proposes Progressive Inference - a framework to compute input attributions to explain the predictions of decoder-only sequence classification models. Our work is based o…
cs.LG2023
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
Sanjay Kariyappa, Leonidas Tsepenekas, Freddy Lécué +1
The SHAP framework provides a principled method to explain the predictions of a model by computing feature importance. Motivated by applications in finance, we introduce the Top-k…