Saved in:
Bibliographic Details
Main Authors: Qiu, Fanxiao Wani, Leong, Oscar, LaTourrette, Alexander
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.03144
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912871778091008
author Qiu, Fanxiao Wani
Leong, Oscar
LaTourrette, Alexander
author_facet Qiu, Fanxiao Wani
Leong, Oscar
LaTourrette, Alexander
contents Teaching requires distilling a rich category distribution into a small set of informative exemplars. Although prior work shows that humans consider both representativeness and diversity when teaching, the computational principles underlying these tradeoffs remain unclear. We address this gap by modeling human exemplar selection using neural network feature representations and principled subset selection criteria. Novel visual categories were embedded along a one-dimensional morph continuum using pretrained vision models, and selection strategies varied in their emphasis on prototypicality, joint representativeness, and diversity. Adult participants selected one to three exemplars to teach a learner. Model-human comparisons revealed that strategies based on joint representativeness, or its combination with diversity, best captured human judgments, whereas purely prototypical or diversity-based strategies performed worse. Moreover, transformer-based representations consistently aligned more closely with human behavior than convolutional networks. These results highlight the potential utility of dataset distillation methods in machine learning as computational models for teaching.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03144
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle What Makes a Good Example? Modeling Exemplar Selection with Neural Network Representations
Qiu, Fanxiao Wani
Leong, Oscar
LaTourrette, Alexander
Machine Learning
Teaching requires distilling a rich category distribution into a small set of informative exemplars. Although prior work shows that humans consider both representativeness and diversity when teaching, the computational principles underlying these tradeoffs remain unclear. We address this gap by modeling human exemplar selection using neural network feature representations and principled subset selection criteria. Novel visual categories were embedded along a one-dimensional morph continuum using pretrained vision models, and selection strategies varied in their emphasis on prototypicality, joint representativeness, and diversity. Adult participants selected one to three exemplars to teach a learner. Model-human comparisons revealed that strategies based on joint representativeness, or its combination with diversity, best captured human judgments, whereas purely prototypical or diversity-based strategies performed worse. Moreover, transformer-based representations consistently aligned more closely with human behavior than convolutional networks. These results highlight the potential utility of dataset distillation methods in machine learning as computational models for teaching.
title What Makes a Good Example? Modeling Exemplar Selection with Neural Network Representations
topic Machine Learning
url https://arxiv.org/abs/2602.03144