ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction

2026-08-18

AI Summary

本文提出ARASH方法，通过局部邻域分析选择最优样本，提高表格预测效率，减少TabPFN的提示长度和内存使用。

Abstract

Tabular prediction is a critical task across numerous applications. The recent success of large language models has sparked various approaches for adapting them to the tabular domain. A prevalent strategy involves training or fine-tuning specialized Tabular Foundation Models (TFMs) such as TabPFN. However, TFMs require substantial computational resources, and frequent model retraining is often impractical. In-context learning (ICL), specifically, few-shot prompting, offers a resource-efficient alternative to enhance performance. Yet, identifying the most relevant rows to serve as shots remains a challenge for tabular data. This paper introduces ARASH (Adaptive, query-specific Retrieval And Shot selection), a method that improves TFM efficiency by selecting optimal shots based on local neighborhood analysis within the training set. Our results demonstrate that ARASH reduces the prompt length and memory usage of TabPFN by 1261.5$\times$ and 2.56$\times$, respectively, while providing comparable accuracy.

Problem

• tabular prediction
• in-context learning
• few-shot prompting
• computational resources
• shot selection

Innovation

• Adaptive Retrieval
• Shot Selection
• Tabular Prediction
• In-context Learning
• Resource Efficiency