{"ID":2883385,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09263","arxiv_id":"2508.09263","title":"LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data","abstract":"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.","short_abstract":"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 fram...","url_abs":"https://arxiv.org/abs/2508.09263","url_pdf":"https://arxiv.org/pdf/2508.09263v1","authors":"[\"Peng Wang\",\"Dongsheng Wang\",\"He Zhao\",\"Hangting Ye\",\"Dandan Guo\",\"Yi Chang\"]","published":"2025-08-12T18:07:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}