# Exemplars in Disguise: Pure Exemplar Models Mimic Abstraction-First Learning

arXiv: https://arxiv.org/abs/2608.00821 · HTML: https://mlsanity.com/paper/2608.00821/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 44 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 2 of 2)

- [Transformers perform adaptive partial pooling](https://mlsanity.com/paper/2602.03980/) (2026)
- [Humans and transformer LMs: Abstraction drives language learning](https://mlsanity.com/paper/2603.17475/) (2026)

## Built on by (most cited first, 1 of 1)

- [Everyone Was Right: Lexical Representations in Language Models Are Both Abstract and Holistic](https://mlsanity.com/paper/2610.17538/) (2026)

## Abstract (arXiv)

Whether idiosyncratic, item-specific knowledge is learned before abstract class-level generalizations, or vice versa, is a central question in language learning, with exemplar and abstraction-based theories making opposite predictions. Recent methods have claimed to show that, at least for large language models, abstract knowledge is learned first. We show that these methods fall short: pure memorizer models with no abstract representations can appear, by the same criteria, to learn either item-specific or class-level knowledge first, depending on their sensitivity to individual observations, with the transition point governed by the distributional properties of the input. We further argue that the distinction between item-specific and abstract knowledge may be ill-defined for distributed representations, as a word's class-level properties may not be separable from its item-specific properties.