论文提出 TANN 与 EPIC 主动上下文学习规则，提升表格基础模型标注效率
When, Where, How: Active In-Context Learning for Tabular Foundation Models
标注数据太贵？这篇论文教你用 TANN 和 EPIC 挑最有价值的行，标注 5-10% 就能达到八成性能，还顺手提升 GBDT。
论文研究表格基础模型（TFM）在上下文学习时如何主动挑选标注行。作者提出 Target-Aware Nearest Neighbor（TANN）获取规则和 Expected Predictive Information Gain in Context（EPIC）方法，与经典获取规则对比。实验覆盖二十个基准，使用两个成熟的 TFM 和经典 GBDT。结果显示 EPIC 只标注 5-10% 的样本池，就能在八个最大样本池基准上保留 80-87% 的 chance-corrected 全量数据性能，且选出的标注也能提升梯度提升树的预测表现。
When, Where, How: Active In-Context Learning for Tabular Foundation Models
Tabular Foundation Models (TFMs) adapt to a new task only through the labeled rows in their context. However, labels are expensive to acquire in real-world scenarios due to the need for highly specific domain knowledge to ensure high-quality data. Active in-context learning transfers classical acquisition rules to this setting, in which the model that guides acquisition changes with every label added. We ask how the value of diversity, predictive uncertainty and target-aware information gain changes as a frozen TFM acquires more context. For that, we study Target-Aware Nearest Neighbor (TANN) acquisition and the Expected Predictive Information Gain in Context (EPIC) and evaluate them against classical rules. Our study across twenty benchmarks with two well-established TFMs and classical GBDTs highlights three findings: (i) When: diversity-based acquisition is best during the first acquisition iterations; (ii) Where: labeling pool rows that serve the target inputs via a simple target-aware nearest-neighbor rule matters substantially; (iii) How: EPIC yields the best models at the label budget, retains on average 80--87% of the chance-corrected full-data performance with only 5-10% of the pool labeled on the eight benchmarks with the largest pools, and selects labels that also improve the predictive performance of gradient-boosted decision trees.