# Can Large Language Models generalize analogy solving like children can?

arXiv: https://arxiv.org/abs/2411.02348 · HTML: https://mlsanity.com/paper/2411.02348/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain](https://mlsanity.com/paper/2305.07141/) (2023)
- [Large Language Models Are Not Strong Abstract Reasoners](https://mlsanity.com/paper/2305.19555/) (2023)
- [Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2402.08955/) (2024)
- [KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models](https://mlsanity.com/paper/2407.17773/) (2024)
- [Evidence from counterfactual tasks supports emergent analogical reasoning in large language models](https://mlsanity.com/paper/2404.13070/) (2024)
- [Response: Emergent analogical reasoning in large language models](https://mlsanity.com/paper/2308.16118/) (2023)
- [Do large language models solve verbal analogies like children do?](https://mlsanity.com/paper/2310.20384/) (2023)
- [A Theory of Relation Learning and Cross-domain Generalization](https://mlsanity.com/paper/1910.05065/) (2019)
- [Do Large Language Models Solve ARC Visual Analogies Like People Do?](https://mlsanity.com/paper/2403.09734/) (2024)

## Built on by (most cited first, 9 of 9)

- [Evaluating the Robustness of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2411.14215/) (2024)
- [We Can't Understand AI Using our Existing Vocabulary](https://mlsanity.com/paper/2502.07586/) (2025)
- [LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning](https://mlsanity.com/paper/2502.11176/) (2025)
- [What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models](https://mlsanity.com/paper/2507.22457/) (2025)
- [Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning](https://mlsanity.com/paper/2508.10057/) (2025)
- [Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models](https://mlsanity.com/paper/2502.12821/) (2025)
- [Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs](https://mlsanity.com/paper/2506.13192/) (2025)
- [Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives](https://mlsanity.com/paper/2603.29997/) (2026)
- [Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning](https://mlsanity.com/paper/2604.06501/) (2026)

## Abstract (arXiv)

In people, the ability to solve analogies such as "body : feet :: table : ?" emerges in childhood, and appears to transfer easily to other domains, such as the visual domain "( : ) :: < : ?". Recent research shows that large language models (LLMs) can solve various forms of analogies. However, can LLMs generalize analogy solving to new domains like people can? To investigate this, we had children, adults, and LLMs solve a series of letter-string analogies (e.g., a b : a c :: j k : ?) in the Latin alphabet, in a near transfer domain (Greek alphabet), and a far transfer domain (list of symbols). Children and adults easily generalized their knowledge to unfamiliar domains, whereas LLMs did not. This key difference between human and AI performance is evidence that these LLMs still struggle with robust human-like analogical transfer.