PulseAugur
LIVE 08:46:08
research · [3 sources] ·
0
research

ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules

Two new research papers introduce methods for better evaluating and cleaning tabular foundation models. ScoringBench offers a comprehensive benchmark using proper scoring rules to assess model performance beyond simple point estimates, revealing how different metrics can lead to varied model rankings. Prior-Aligned Data Cleaning, on the other hand, proposes a deep reinforcement learning framework to clean real-world tabular data, addressing issues like missing values and outliers to improve model accuracy and confidence calibration. AI

Summary written by None from 3 sources. How we write summaries →

IMPACT New evaluation and data cleaning techniques could improve the reliability and deployment of tabular foundation models in high-stakes applications.

RANK_REASON The cluster contains two academic papers introducing new benchmarks and methodologies for tabular foundation models.

Read on arXiv cs.AI →

COVERAGE [3]

  1. arXiv cs.LG TIER_1 · Laure Berti-Equille ·

    Prior-Aligned Data Cleaning for Tabular Foundation Models

    arXiv:2604.25154v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating processes -- making them highly attractive for practitioners who cannot afford la…

  2. arXiv cs.AI TIER_1 · Jonas Landsgesell, Pascal Knoll, Tizian Wenzel ·

    ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules

    arXiv:2603.29928v2 Announce Type: replace Abstract: Tabular foundation models such as TabPFN and TabICL already produce full predictive distributions, yet prevailing regression benchmarks evaluate them almost exclusively via point-estimate metrics (RMSE, $R^2$). This discards pre…

  3. arXiv cs.LG TIER_1 · Laure Berti-Equille ·

    Prior-Aligned Data Cleaning for Tabular Foundation Models

    Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating processes -- making them highly attractive for practitioners who cannot afford large annotated corpora. However, their in-context…