LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data
Not on the map. Why?
Abstract (arXiv)
Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing advanced LLMs in few-shot and even zero-shot scenarios is still challenging. To this end, we propose a novel LLM-based prototype estimation framework for tabular learning. Our key idea is to query the LLM to generate feature values based example-free prompt, which solely relies on task and feature descriptions. With the feature values generated by LLM, we can build a zero-shot prototype in a training-free manner, which can be further enhanced by fusing few-shot samples, avoiding training a classifier or finetuning the LLMs. Thanks to the example-free prompt and prototype estimation, ours bypasses the constraints brought by the example-based prompt, providing a scalable and robust framework. Extensive experiments demonstrate the effectiveness of ours in zero and few-shot tabular learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 12 Aug 2025.
Builds on
30 of 48 references.
References · 30
- 2023GPT-4 Technical Reportcited by 18,132
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
- 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
- 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
- 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
- 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
- 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
- 2023Faithful Chain-of-Thought Reasoningcited by 285
- 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 273
18 more
- 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
- 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
- 2023Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineeringcited by 125
- 2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 79
- 2020Towards Domain-Agnostic Contrastive Learningcited by 75
- 2020Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Datacited by 52
- 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
- 2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tablescited by 48
- 2023FinDiff: Diffusion Models for Financial Tabular Data Generationcited by 41
- 2020Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Datacited by 37
- 2023Large Language Models Are Zero-Shot Text Classifierscited by 35
- 2023TABLET: Learning From Instructions For Tabular Datacited by 28
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
- 2024PTaRL: Prototype-based Tabular Representation Learning via Space Calibrationcited by 27
- 2023Tuning Multi-mode Token-level Prompt Alignment across Modalitiescited by 26
- 2023Language models are weak learnerscited by 21
- 2020Trajectories, bifurcations and pseudotime in large clinical datasets: applications to myocardial infarction and diabetes datacited by 13
- 2024Tabular Transfer Learning via Prompting LLMscited by 10
Built on by
Citing papers per year: 2026: 2.
2 papers.