表格AI只在简单任务上强，复杂场景还得靠老方法
AI圈最近热捧的「表格基础模型」——那种能处理表格数据的通用大模型——其实只在特定场景下厉害。研究者搞了个统一评测，测试了11个模型和142个数据集，发现这些新模型只在数据量小、分布简单（IID）的任务上表现好；一旦遇到数据量大、维度高、或者有时间序列等复杂情况，传统的树模型和深度学习模型反而更强。换句话说，新模型还没真正「通用」，它们擅长的是实验室里的简单题，现实中的难题还得靠老办法。这不是你明天能用上的技术，但它提醒你：别被「基础模型」的名头唬住，选工具要看具体场景。
📄 原文摘要(英文)
Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are increasingly evaluating tabular foundation models on diverse datasets and tasks. However, these task- and discipline-specific evaluations remain largely inaccessible to model researchers because benchmark software and evaluation protocols are fragmented. As a result, model researchers rely on standard benchmarks, which are mostly defined for tasks where tabular foundation models already excel. The most challenging scenarios are excluded, limiting meaningful progress in the field by focusing on marginal improvements on IID data rather than on broader, more demanding challenges. To overcome this, we introduce BeyondArena, the first unified holistic benchmark for tabular data that supports diverse task types (IID, temporal, grouped), across sample size and feature dimensionality scales, with diverse feature types (with text, with high cardinality) from a broad range of disciplines. To enable unified benchmarking beyond standard benchmarks, we introduce Data Foundry, a Python framework and metadata schema for curating tabular datasets for predictive machine learning. Our results across 11 models and 142 curated datasets show that existing tabular foundation models excel on tiny- to medium-sized IID data, while traditional tree-based and deep learning models still dominate on non-IID, large, and high-dimensional datasets. BeyondArena guides model research for the most demanding challenges in tabular data, enabling progress towards truly foundational tabular models.