mlsanityData to 7 Oct 2026

TABLET: Learning From Instructions For Tabular Data

arXiv 2304.13188 ↗First posted 25 Apr 2023cs.LG cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

Acquiring high-quality data is often a significant challenge in training machine learning (ML) models for tabular prediction, particularly in privacy-sensitive and costly domains like medicine and finance. Providing natural language instructions to large language models (LLMs) offers an alternative solution. However, it is unclear how effectively instructions leverage the knowledge in LLMs for solving tabular prediction problems. To address this gap, we introduce TABLET, a benchmark of 20 diverse tabular datasets annotated with instructions that vary in their phrasing, granularity, and technicality. Additionally, TABLET includes the instructions' logic and structured modifications to the instructions. We find in-context instructions increase zero-shot F1 performance for Flan-T5 11b by 44% on average and 13% for ChatGPT on TABLET. Also, we explore the limitations of using LLMs for tabular prediction in our benchmark by evaluating instruction faithfulness. We find LLMs often ignore instructions and fail to predict specific instances correctly, even with examples. Our analysis on TABLET shows that, while instructions help LLM performance, learning from instructions for tabular data requires new capabilities.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 21 of its 41 references that are in the map. First posted on arXiv 25 Apr 2023.

Builds on

21 of 41 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  4. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  5. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  6. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  7. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  8. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  9. 2021MetaICL: Learning to Learn In Contextcited by 450
  10. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 398
  11. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  12. 2022Language Models are Realistic Tabular Data Generatorscited by 290
9 more
  1. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 273
  2. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  3. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
  4. 2022Can Foundation Models Wrangle Your Data?cited by 173
  5. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  6. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  7. 2021Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collectionscited by 128
  8. 2022DDXPlus: A New Dataset For Automatic Medical Diagnosiscited by 87
  9. 2022Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learnerscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 9; 2025: 12; 2026: 5.

28 papers.

Sort:

By area:

  1. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 271
  2. 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 79
  3. 2024Evaluating language models as risk scorescited by 24
  4. 2024Emergency Department Decision Support using Clinical Pseudo-notescited by 22
  5. 2024Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolutioncited by 19
  6. 2023Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classificationscited by 15
  7. 2024Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretrainingcited by 12
  8. 2024DP-TabICL: In-Context Learning with Differentially Private Tabular Datacited by 11
  9. 2024Improving LLM Group Fairness on Tabular Data via In-Context Learningcited by 6
  10. 2025Emergent Bias and Fairness in Multi-Agent Decision Systemscited by 5
  11. 2025Transfer Learning of Tabular Data by Finetuning Large Language Modelscited by 4
  12. 2025Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizescited by 4
16 more
  1. 2026FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learningcited by 4
  2. 2024Reasoning Factual Knowledge in Structured Data with Large Language Modelscited by 3
  3. 2024LLM Embeddings Improve Test-time Adaptation to Tabular Y|X-Shiftscited by 3
  4. 2025Embedding Domain-Specific Knowledge from LLMs into the Feature Engineering Pipelinecited by 3
  5. 2025Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learningcited by 3
  6. 2025Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMscited by 3
  7. 2025LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Datacited by 2
  8. 2025Large Language Models as Attribution Regularizers for Efficient Model Trainingcited by 1
  9. 2026ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffoldcited by 1
  10. 2025Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classificationcited by 0
  11. 2025Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddingscited by 0
  12. 2025SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validationcited by 0
  13. 2025Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classificationcited by 0
  14. 2026LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shotscited by 0
  15. 2026TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learningcited by 0
  16. 2026Marginal Response Surface Elicitation for Zero-Label Tabular Learningcited by 0