# Do large language models solve verbal analogies like children do?

arXiv: https://arxiv.org/abs/2310.20384 · HTML: https://mlsanity.com/paper/2310.20384/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 67 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [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)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [mGPT: Few-Shot Learners Go Multilingual](https://mlsanity.com/paper/2204.07580/) (2022)
- [BERTje: A Dutch BERT Model](https://mlsanity.com/paper/1912.09582/) (2019)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [RobBERT: a Dutch RoBERTa-based Language Model](https://mlsanity.com/paper/2001.06286/) (2020)
- [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://mlsanity.com/paper/2301.10472/) (2023)
- [BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?](https://mlsanity.com/paper/2105.04949/) (2021)
- [As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages](https://mlsanity.com/paper/2012.05628/) (2020)
- [Distilling Relation Embeddings from Pre-trained Language Models](https://mlsanity.com/paper/2110.15705/) (2021)
- [Probabilistic Analogical Mapping with Semantic Relation Networks](https://mlsanity.com/paper/2103.16704/) (2021)
- [Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance](https://mlsanity.com/paper/2310.05597/) (2023)
- [Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource](https://mlsanity.com/paper/1607.00225/) (2016)

## Built on by (most cited first, 13 of 13)

- [Can Large Language Models generalize analogy solving like children can?](https://mlsanity.com/paper/2411.02348/) (2024)
- [Do Large Language Models Solve ARC Visual Analogies Like People Do?](https://mlsanity.com/paper/2403.09734/) (2024)
- [Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning](https://mlsanity.com/paper/2412.05586/) (2024)
- [Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences](https://mlsanity.com/paper/2511.02109/) (2025)
- [Automatic Extraction of Metaphoric Analogies from Literary Texts: Task Formulation, Dataset Construction, and Evaluation](https://mlsanity.com/paper/2412.15375/) (2024)
- [Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions](https://mlsanity.com/paper/2503.16468/) (2025)
- [Modelling Analogies and Analogical Reasoning: Connecting Cognitive Science Theory and NLP Research](https://mlsanity.com/paper/2509.09381/) (2025)
- [Enhancing multimodal analogical reasoning with Logic Augmented Generation](https://mlsanity.com/paper/2504.11190/) (2025)
- [The Medical Metaphors Corpus (MCC)](https://mlsanity.com/paper/2508.07993/) (2025)
- [Large Language Models provide support for the parallelogram theory of analogy](https://mlsanity.com/paper/2603.19066/) (2026)
- [Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning](https://mlsanity.com/paper/2604.06501/) (2026)
- [Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid](https://mlsanity.com/paper/2605.01359/) (2026)
- [Playing with Words, Improving with Rewards: Training Language Models for Creative Association](https://mlsanity.com/paper/2605.27832/) (2026)

## Abstract (arXiv)

Analogy-making lies at the heart of human cognition. Adults solve analogies such as textitHorse belongs to stable like chicken belongs to ...? by mapping relations (textitkept in) and answering textitchicken coop. In contrast, children often use association, e.g., answering textitegg. This paper investigates whether large language models (LLMs) solve verbal analogies in A:B::C:? form using associations, similar to what children do. We use verbal analogies extracted from an online adaptive learning environment, where 14,002 7-12 year-olds from the Netherlands solved 622 analogies in Dutch. The six tested Dutch monolingual and multilingual LLMs performed around the same level as children, with MGPT performing worst, around the 7-year-old level, and XLM-V and GPT-3 the best, slightly above the 11-year-old level. However, when we control for associative processes this picture changes and each model's performance level drops 1-2 years. Further experiments demonstrate that associative processes often underlie correctly solved analogies. We conclude that the LLMs we tested indeed tend to solve verbal analogies by association with C like children do.