Hugging Face Trending Papers
Lost in Aggregation: How Benchmarks Overlook Irreplaceable Model Strengths
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Aug 20
Lost in Aggregation: How Benchmarks Overlook Irreplaceable Model Strengths
The paper argues that typical tabular machine learning benchmarks, which aggregate results by averaging scores or ranks, can hide which models are essential for achieving the best performance on specific datasets. It proposes evaluating models against a data‑centric peak performance frontier, classifying them as irreplaceable, sufficient, redundant, or fallible based on their position relative to other models. Applying this to the TabArena benchmark shows that common aggregation metrics mainly capture consistency and failure avoidance, but fail to reflect dataset‑specific strengths, leading to a misalignment between aggregate rewards and true model utility.
arXiv Machine Learning
Jun 29
Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings
arXiv:2606. 27997v1 Announce Type: new Abstract: Benchmarks of machine learning models often include many datasets, making evaluation expensive.
arXiv AI
Jun 4
Position: State-of-the-Art Claims Require State-of-the-Art Evidence
arXiv:2605. 17273v3 Announce Type: replace-cross Abstract: State-of-the-Art (SOTA) claims pervade Artificial Intelligence (AI) and Machine Learning (ML) research.
arXiv AI
Jun 30
Beyond IID: How General Are Tabular Foundation Models, Really?
arXiv:2606. 30410v1 Announce Type: cross Abstract: Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry.
arXiv Machine Learning
Jun 2
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
arXiv:2606. 02384v1 Announce Type: new Abstract: Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures.
arXiv AI
Jun 4
Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning
arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.