New arXiv work proposes incorporating human-based feature understandability directly into feature selection for tabular XAI, aiming to generate more accessible natural language explanations rather than only evaluating them…

#AI #XAI #HumanCentredAI #TabularData
https://arxiv.org/abs/2610.16627

New arXiv work introduces LATTEArena, a standardized benchmarking framework for evaluating LLM-powered tabular feature engineering methods, covering 24 core configurations across 7 research questions. Aims to address…

#AI #MachineLearning #TabularData #Benchmarking
https://arxiv.org/abs/2606.09004

New arXiv paper systematically re-evaluates regression objectives for tabular deep learning, finding many proposed alternatives offer limited gains over tuned MSE, while quantile loss shows consistent improvements. The…

#TabularData #DeepLearning #Regression #ArXiv
https://arxiv.org/abs/2610.13909

SelectArena is a new benchmark for feature selection on real-world tabular data, addressing limitations of outdated models and artificial datasets in prior evaluations.

#MachineLearning #FeatureSelection #TabularData #AIResearch
https://arxiv.org/abs/2610.13644