# Studies with impossible languages falsify LMs as models of human language

arXiv: https://arxiv.org/abs/2511.11389 · HTML: https://mlsanity.com/paper/2511.11389/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2025.

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

- [An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal](https://mlsanity.com/paper/2604.18293/) (2026)
- [Informational Antilocality and the Locality Bias in LLMs](https://mlsanity.com/paper/2608.27760/) (2026)

## Abstract (arXiv)

According to Futrell and Mahowald [arXiv:2501.17047], both infants and language models (LMs) find attested languages easier to learn than impossible languages that have unnatural structures. We review the literature and show that LMs often learn attested and many impossible languages equally well. Difficult to learn impossible languages are simply more complex (or random). LMs are missing human inductive biases that support language acquisition.