Gatsby Without the 'E': Crafting Lipograms with LLMs

2025-05-26

AI Summary

This study investigates the capability of large language models (LLMs) to generate lipograms—texts deliberately omitting specified letters—under extreme character constraints, using *The Great Gatsby* as a testbed to produce high-quality, fully “e”-free rewrites. Methodologically, we propose a synergistic framework integrating synonym substitution baselines, an enhanced generative architecture, named-entity-aware rewriting, and beam search decoding. We conduct the first systematic evaluation of LLM-generated multi-level lipograms, ordered by letter frequency rank; results reveal that omitting the top 3.6% most frequent English letters (up to and including “e”) preserves near-native semantic coherence, while stricter constraints induce predictable degradation in semantic fidelity. Our work not only demonstrates linguistic resilience under severe structural constraints but also establishes a quantifiable relationship between constraint intensity and generation quality—advancing controllable text generation and computational stylistics with a novel empirical paradigm.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Transforming The Great Gatsby into an 'e'-less lipogram using LLMs
• Evaluating impact of letter exclusion on text meaning and fidelity
• Exploring techniques for constrained writing with modern language models

Innovation

• Synonym replacement for lipogram creation
• Beam search enhanced generative models
• Named entity analysis for text fidelity