# Human few-shot learning of compositional instructions

arXiv: https://arxiv.org/abs/1901.04587 · HTML: https://mlsanity.com/paper/1901.04587/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2019.

## Built on by (most cited first, 30 of 47)

- [What Artificial Neural Networks Can Tell Us About Human Language Acquisition](https://mlsanity.com/paper/2208.07998/) (2022)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [The paradox of the compositionality of natural language: a neural machine translation case study](https://mlsanity.com/paper/2108.05885/) (2021)
- [PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns](https://mlsanity.com/paper/2403.13315/) (2024)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [Bayesian Preference Elicitation with Language Models](https://mlsanity.com/paper/2403.05534/) (2024)
- [Fast and flexible: Human program induction in abstract reasoning tasks](https://mlsanity.com/paper/2103.05823/) (2021)
- [Lexicon Learning for Few-Shot Neural Sequence Modeling](https://mlsanity.com/paper/2106.03993/) (2021)
- [Symbolic Behaviour in Artificial Intelligence](https://mlsanity.com/paper/2102.03406/) (2021)
- [Revisiting the Compositional Generalization Abilities of Neural Sequence Models](https://mlsanity.com/paper/2203.07402/) (2022)
- [When does compositional structure yield compositional generalization? A kernel theory](https://mlsanity.com/paper/2405.16391/) (2024)
- [Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation](https://mlsanity.com/paper/2408.16228/) (2024)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [On The Specialization of Neural Modules](https://mlsanity.com/paper/2409.14981/) (2024)
- [Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following](https://mlsanity.com/paper/2502.05454/) (2025)
- [A Survey on Compositional Generalization in Applications](https://mlsanity.com/paper/2302.01067/) (2023)
- [Learning Symbolic Rules for Reasoning in Quasi-Natural Language](https://mlsanity.com/paper/2111.12038/) (2021)
- [InductionBench: LLMs Fail in the Simplest Complexity Class](https://mlsanity.com/paper/2502.15823/) (2025)
- [Compositionality as Lexical Symmetry](https://mlsanity.com/paper/2201.12926/) (2022)
- [Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality](https://mlsanity.com/paper/2211.15578/) (2022)
- [Compositional diversity in visual concept learning](https://mlsanity.com/paper/2305.19374/) (2023)
- [Can Humans Do Less-Than-One-Shot Learning?](https://mlsanity.com/paper/2202.04670/) (2022)
- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [Schr"odinger's Tree -- On Syntax and Neural Language Models](https://mlsanity.com/paper/2110.08887/) (2021)
- [Interpretable Learned Emergent Communication for Human-Agent Teams](https://mlsanity.com/paper/2201.07452/) (2022)
- [One-Shot Learning from a Demonstration with Hierarchical Latent Language](https://mlsanity.com/paper/2203.04806/) (2022)
- [Modelling the development of counting with memory-augmented neural networks](https://mlsanity.com/paper/2105.10577/) (2021)
- [Im-Promptu: In-Context Composition from Image Prompts](https://mlsanity.com/paper/2305.17262/) (2023)

## Abstract (arXiv)

People learn in fast and flexible ways that have not been emulated by machines. Once a person learns a new verb "dax," he or she can effortlessly understand how to "dax twice," "walk and dax," or "dax vigorously." There have been striking recent improvements in machine learning for natural language processing, yet the best algorithms require vast amounts of experience and struggle to generalize new concepts in compositional ways. To better understand these distinctively human abilities, we study the compositional skills of people through language-like instruction learning tasks. Our results show that people can learn and use novel functional concepts from very few examples (few-shot learning), successfully applying familiar functions to novel inputs. People can also compose concepts in complex ways that go beyond the provided demonstrations. Two additional experiments examined the assumptions and inductive biases that people make when solving these tasks, revealing three biases: mutual exclusivity, one-to-one mappings, and iconic concatenation. We discuss the implications for cognitive modeling and the potential for building machines with more human-like language learning capabilities.