Research

Paper

AI LLM February 27, 2026

The Astonishing Ability of Large Language Models to Parse Jabberwockified Language

Authors

Gary Lupyan, Senyi Yang

Abstract

We show that large language models (LLMs) have an astonishing ability to recover meaning from severely degraded English texts. Texts in which content words have been randomly substituted by nonsense strings, e.g., "At the ghybe of the swuint, we are haiveed to Wourge Phrear-gwurr, who sproles into an ghitch flount with his crurp", can be translated to conventional English that is, in many cases, close to the original text, e.g., "At the start of the story, we meet a man, Chow, who moves into an apartment building with his wife." These results show that structural cues (e.g., morphosyntax, closed-class words) constrain lexical meaning to a much larger degree than imagined. Although the abilities of LLMs to make sense of "Jabberwockified" English are clearly superhuman, they are highly relevant to understanding linguistic structure and suggest that efficient language processing either in biological or artificial systems likely benefits from very tight integration between syntax, lexical semantics, and general world knowledge.

Metadata

arXiv ID: 2602.23928
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.23928v1</id>\n    <title>The Astonishing Ability of Large Language Models to Parse Jabberwockified Language</title>\n    <updated>2026-02-27T11:23:45Z</updated>\n    <link href='https://arxiv.org/abs/2602.23928v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.23928v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We show that large language models (LLMs) have an astonishing ability to recover meaning from severely degraded English texts. Texts in which content words have been randomly substituted by nonsense strings, e.g., \"At the ghybe of the swuint, we are haiveed to Wourge Phrear-gwurr, who sproles into an ghitch flount with his crurp\", can be translated to conventional English that is, in many cases, close to the original text, e.g., \"At the start of the story, we meet a man, Chow, who moves into an apartment building with his wife.\" These results show that structural cues (e.g., morphosyntax, closed-class words) constrain lexical meaning to a much larger degree than imagined. Although the abilities of LLMs to make sense of \"Jabberwockified\" English are clearly superhuman, they are highly relevant to understanding linguistic structure and suggest that efficient language processing either in biological or artificial systems likely benefits from very tight integration between syntax, lexical semantics, and general world knowledge.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-02-27T11:23:45Z</published>\n    <arxiv:comment>Submitted to the 2026 Annual Meeting of the Cognitive Science Society</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Gary Lupyan</name>\n    </author>\n    <author>\n      <name>Senyi Yang</name>\n    </author>\n  </entry>"
}