5 papers
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
Carmen Quiles-RamÃrez, Leticia L. RodrÃguez, Nicolás Martorell +1
In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains o…
Low-cost concept-based localized explanations: How far can we get with training-free approaches?
Darian Fernández-Gutiérrez, Rafael Bello, Marilyn Bello +1
Concept-based Explainable AI (C-XAI) seeks human-understandable explanations grounded in semantic concepts, yet validation is limited by the scarcity of fine-grained concept annota…
SLU-2K: A Question-Based Benchmark for Semantic Evaluation of Sign Language Translation
Zeno Testa, Antonino Furnari, Lorenzo Baraldi +1
Sign Language Translation (SLT) is typically evaluated with surface-form metrics such as BLEU and ROUGE, which reward lexical overlap but do not directly measure whether a translat…
The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic
Dominika Agnieszka DÅugosz, Arlindo Oliveira, Natalia DÃaz-RodrÃguez
The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-generated variants of GSM8K…
CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs
David Méndez, Gianpaolo Bontempo, Elisa Ficarra +2
Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts a…