# Can Humans Do Less-Than-One-Shot Learning?

arXiv: https://arxiv.org/abs/2202.04670 · HTML: https://mlsanity.com/paper/2202.04670/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 9 Feb 2022.

## Builds on (most cited first, 5 of 5)

- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Soft-Label Dataset Distillation and Text Dataset Distillation](https://mlsanity.com/paper/1910.02551/) (2019)
- [Human few-shot learning of compositional instructions](https://mlsanity.com/paper/1901.04587/) (2019)
- [People infer recursive visual concepts from just a few examples](https://mlsanity.com/paper/1904.08034/) (2019)
- [One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes](https://mlsanity.com/paper/2102.07834/) (2021)

## Built on by (most cited first, 7 of 7)

- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [On the Informativeness of Supervision Signals](https://mlsanity.com/paper/2211.01407/) (2022)
- [BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models](https://mlsanity.com/paper/2512.10932/) (2025)
- [Representational Alignment Supports Effective Machine Teaching](https://mlsanity.com/paper/2406.04302/) (2024)
- [Dynamic Label Injection for Imbalanced Industrial Defect Segmentation](https://mlsanity.com/paper/2408.10031/) (2024)
- [Learning New Tasks from a Few Examples with Soft-Label Prototypes](https://mlsanity.com/paper/2210.17437/) (2022)
- [The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks](https://mlsanity.com/paper/2405.08695/) (2024)

## Abstract (arXiv)

Being able to learn from small amounts of data is a key characteristic of human intelligence, but exactly em how small? In this paper, we introduce a novel experimental paradigm that allows us to examine classification in an extremely data-scarce setting, asking whether humans can learn more categories than they have exemplars (i.e., can humans do "less-than-one shot" learning?). An experiment conducted using this paradigm reveals that people are capable of learning in such settings, and provides several insights into underlying mechanisms. First, people can accurately infer and represent high-dimensional feature spaces from very little data. Second, having inferred the relevant spaces, people use a form of prototype-based categorization (as opposed to exemplar-based) to make categorical inferences. Finally, systematic, machine-learnable patterns in responses indicate that people may have efficient inductive biases for dealing with this class of data-scarce problems.