3 papers
cs.LG2026
Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models
Jose Vinicius Ribeiro, Rafael Figueira Goncalves, Fabio Luiz Melquiades +1
Spectral-based machine learning models have been increasingly deployed in chemometrics and spectroscopy, where predictive accuracy is as important as explainability. Current employ…
cs.CL2024
Are Large Language Models the New Interface for Data Pipelines?
Sylvio Barbon Junior, Paolo Ceravolo, Sven Groppe +5
A Language Model is a term that encompasses various types of models designed to understand and generate human communication. Large Language Models (LLMs) have gained significant at…
cs.LG2024
Decision Predicate Graphs: Enhancing Interpretability in Tree Ensembles
Leonardo Arrighi, Luca Pennella, Gabriel Marques Tavares +1
Understanding the decisions of tree-based ensembles and their relationships is pivotal for machine learning model interpretation. Recent attempts to mitigate the human-in-the-loop…