mlsanityData to 14 Oct 2026

ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction

arXiv 2608.17856 ↗First posted 18 Aug 2026cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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× and 2.56×, respectively, while providing comparable accuracy.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 18 Aug 2026.

Builds on

25 of 35 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  4. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  5. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  6. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  7. 2017Self-Normalizing Neural Networkscited by 598
  8. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  9. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
  10. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
  11. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 319
  12. 2025TabICL: A Tabular Foundation Model for In-Context Learning on Large Datacited by 289
13 more
  1. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 277
  2. 2017OpenML Benchmarking Suitescited by 178
  3. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  4. 2024TabDPT: Scaling Tabular Foundation Models on Real Datacited by 113
  5. 2023TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023cited by 74
  6. 2024Retrieval & Fine-Tuning for In-Context Tabular Modelscited by 59
  7. 2024TALENT: A Tabular Analytics and Learning Toolboxcited by 52
  8. 2021DANets: Deep Abstract Networks for Tabular Data Classification and Regressioncited by 50
  9. 2023kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inferencecited by 47
  10. 2020Gradient Boosting Neural Networks: GrowNetcited by 46
  11. 2024SwitchTab: Switched Autoencoders Are Effective Tabular Learnerscited by 38
  12. 2023TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specializationcited by 32
  13. 2024PTaRL: Prototype-based Tabular Representation Learning via Space Calibrationcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Compile the Table: Query-Calibrated Operator Compression for Tabular In-Context Learningcited by 0