Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet
中文摘要
表格基础模型可零样本预测电子表格缺失列，在TabArena基准测试中超越了调优后的梯度提升树，但XGBoost在部分场景仍占优势。
English Summary
Tabular foundation models predict spreadsheet columns zero-shot, surpassing tuned gradient-boosted trees on TabArena, while noting where XGBoost still maintains an advantage.
原文节选
Tabular foundation models predict the missing column of any spreadsheet zero-shot, the way an LLM completes text — and on the TabArena benchmark they now sit above fully tuned gradient-boosted trees. An introduction to how they work, an independent reproduction of the strongest open one, and a map of where XGBoost still wins. The post Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet appeared first on Towards Data Science.