Saved in:
Bibliographic Details
Main Authors: Han, Shuchu, Bruckner, Wolfgang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.20451
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909659974074368
author Han, Shuchu
Bruckner, Wolfgang
author_facet Han, Shuchu
Bruckner, Wolfgang
contents A fundamental question in applying In-Context Learning (ICL) for tabular data classification is how to determine the ideal number of demonstrations in the prompt. This work addresses this challenge by presenting an algorithm to automatically select a reasonable number of required demonstrations. Our method distinguishes itself by integrating not only the tabular data's distribution but also the user's selected prompt template and the specific Large Language Model (LLM) into its estimation. Rooted in Spectral Graph Theory, our proposed algorithm defines a novel metric to quantify the similarities between different demonstrations. We then construct a similarity graph and analyze the eigenvalues of its Laplacian to derive the minimum number of demonstrations capable of representing the data within the LLM's intrinsic representation space. We validate the efficacy of our approach through experiments comparing its performance against conventional random selection algorithms on diverse datasets and LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20451
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic Demonstration Selection for LLM-based Tabular Data Classification
Han, Shuchu
Bruckner, Wolfgang
Machine Learning
Artificial Intelligence
A fundamental question in applying In-Context Learning (ICL) for tabular data classification is how to determine the ideal number of demonstrations in the prompt. This work addresses this challenge by presenting an algorithm to automatically select a reasonable number of required demonstrations. Our method distinguishes itself by integrating not only the tabular data's distribution but also the user's selected prompt template and the specific Large Language Model (LLM) into its estimation. Rooted in Spectral Graph Theory, our proposed algorithm defines a novel metric to quantify the similarities between different demonstrations. We then construct a similarity graph and analyze the eigenvalues of its Laplacian to derive the minimum number of demonstrations capable of representing the data within the LLM's intrinsic representation space. We validate the efficacy of our approach through experiments comparing its performance against conventional random selection algorithms on diverse datasets and LLMs.
title Automatic Demonstration Selection for LLM-based Tabular Data Classification
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.20451