# Minimization of Boolean Complexity in In-Context Concept Learning

arXiv: https://arxiv.org/abs/2412.02823 · HTML: https://mlsanity.com/paper/2412.02823/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 16 references that are in the map.
- First posted on arXiv 3 Dec 2024.

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

- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)

## Built on by (most cited first, 2 of 2)

- [Uncovering Implicit Bias in Large Language Models with Concept Learning Dataset](https://mlsanity.com/paper/2510.01219/) (2025)
- [LLMs Learn Better In-Context from Rules than from Examples](https://mlsanity.com/paper/2609.03213/) (2026)

## Abstract (arXiv)

What factors contribute to the relative success and corresponding difficulties of in-context learning for Large Language Models (LLMs)? Drawing on insights from the literature on human concept learning, we test LLMs on carefully designed concept learning tasks, and show that task performance highly correlates with the Boolean complexity of the concept. This suggests that in-context learning exhibits a learning bias for simplicity in a way similar to humans.