Gatsby Without the 'E': Crafting Lipograms with LLMs

TL;DR

This paper demonstrates how large language models can effectively create lipograms, specifically transforming The Great Gatsby into an 'e'-less version, revealing language flexibility under strict constraints.

Contribution

It introduces methods for generating lipograms using LLMs, including baseline and advanced techniques, and analyzes the impact of letter exclusion on text fidelity.

Findings

Excluding up to 3.6% of common letters minimally affects meaning

Translation fidelity decreases rapidly with stronger constraints

LLMs show surprising flexibility in constrained text generation

Abstract

Lipograms are a unique form of constrained writing where all occurrences of a particular letter are excluded from the text, typified by the novel Gadsby, which daringly avoids all usage of the letter 'e'. In this study, we explore the power of modern large language models (LLMs) by transforming the novel F. Scott Fitzgerald's The Great Gatsby into a fully 'e'-less text. We experimented with a range of techniques, from baseline methods like synonym replacement to sophisticated generative models enhanced with beam search and named entity analysis. We show that excluding up to 3.6% of the most common letters (up to the letter 'u') had minimal impact on the text's meaning, although translation fidelity rapidly and predictably decays with stronger lipogram constraints. Our work highlights the surprising flexibility of English under strict constraints, revealing just how adaptable and creative language can be.