# Large language models and (non-)linguistic recursion

arXiv: https://arxiv.org/abs/2306.07195 · HTML: https://mlsanity.com/paper/2306.07195/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 26 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 4 of 4)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Prompting is not a substitute for probability measurements in large language models](https://mlsanity.com/paper/2305.13264/) (2023)
- [Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humans](https://mlsanity.com/paper/2006.11098/) (2020)
- [PuzzLing Machines: A Challenge on Learning From Small Data](https://mlsanity.com/paper/2004.13161/) (2020)

## Built on by (most cited first, 5 of 5)

- [Language Models as Models of Language](https://mlsanity.com/paper/2408.07144/) (2024)
- [BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2309.06085/) (2023)
- [Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking](https://mlsanity.com/paper/2307.16806/) (2023)
- [Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models](https://mlsanity.com/paper/2504.01589/) (2025)
- [UniGlyph: A Seven-Segment Script for Universal Language Representation](https://mlsanity.com/paper/2410.08974/) (2024)

## Abstract (arXiv)

Recursion is one of the hallmarks of human language. While many design features of language have been shown to exist in animal communication systems, recursion has not. Previous research shows that GPT-4 is the first large language model (LLM) to exhibit metalinguistic abilities (Beguvs, Dkabkowski, and Rhodes 2023). Here, we propose several prompt designs aimed at eliciting and analyzing recursive behavior in LLMs, both linguistic and non-linguistic. We demonstrate that when explicitly prompted, GPT-4 can both produce and analyze recursive structures. Thus, we present one of the first studies investigating whether meta-linguistic awareness of recursion -- a uniquely human cognitive property -- can emerge in transformers with a high number of parameters such as GPT-4.