4 papers
How to Evaluate and Refine your CAM
Luca Domeniconi, Alessandra Stramiglio, Michele Lombardi +1
Class attribution maps (CAMs) provide local explanations for the decisions of convolutional neural networks. While widely used in practice, the evaluation of CAMs remains challengi…
Is General-Purpose AI Reasoning Sensitive to Data-Induced Cognitive Biases? Dynamic Benchmarking on Typical Software Engineering Dilemmas
Francesco Sovrano, Gabriele Dominici, Rita Sevastjanova +2
Human cognitive biases in software engineering can lead to costly errors. While general-purpose AI (GPAI) systems may help mitigate these biases due to their non-human nature, thei…
Explicit vs. Implicit Biographies: Evaluating and Adapting LLM Information Extraction on Wikidata-Derived Texts
Alessandra Stramiglio, Andrea Schimmenti, Valentina Pasqual +3
Text Implicitness has always been challenging in Natural Language Processing (NLP), with traditional methods relying on explicit statements to identify entities and their relations…
Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models
Tuwe Löfström, Fatima Rabia Yapicioglu, Alessandra Stramiglio +2
This paper introduces Fast Calibrated Explanations, a method designed for generating rapid, uncertainty-aware explanations for machine learning models. By incorporating perturbatio…