[2602.15678] Revisiting Northrop Frye's Four Myths Theory with Large Language Models
Summary
This paper explores Northrop Frye's Four Myths Theory through the lens of Large Language Models (LLMs), proposing a character function framework that enhances narrative analysis by focusing on archetypal roles across genres.
Why It Matters
The study bridges literary theory and computational linguistics, offering insights into how LLMs can enhance narrative understanding and generation. It highlights the potential for AI to analyze and create complex narratives, which is crucial for advancements in interactive storytelling and AI-driven content creation.
Key Takeaways
- Introduces a character function framework based on Frye's narrative genres.
- Validates the framework using six LLMs across 40 narrative works.
- Demonstrates high accuracy in recognizing character-role correspondences.
- Highlights variations in performance based on genre and role.
- Suggests implications for future narrative generation and interactive storytelling.
Computer Science > Computation and Language arXiv:2602.15678 (cs) [Submitted on 17 Feb 2026] Title:Revisiting Northrop Frye's Four Myths Theory with Large Language Models Authors:Edirlei Soares de Lima, Marco A. Casanova, Antonio L. Furtado View a PDF of the paper titled Revisiting Northrop Frye's Four Myths Theory with Large Language Models, by Edirlei Soares de Lima and 2 other authors View PDF HTML (experimental) Abstract:Northrop Frye's theory of four fundamental narrative genres (comedy, romance, tragedy, satire) has profoundly influenced literary criticism, yet computational approaches to his framework have focused primarily on narrative patterns rather than character functions. In this paper, we present a new character function framework that complements pattern-based analysis by examining how archetypal roles manifest differently across Frye's genres. Drawing on Jungian archetype theory, we derive four universal character functions (protagonist, mentor, antagonist, companion) by mapping them to Jung's psychic structure components. These functions are then specialized into sixteen genre-specific roles based on prototypical works. To validate this framework, we conducted a multi-model study using six state-of-the-art Large Language Models (LLMs) to evaluate character-role correspondences across 40 narrative works. The validation employed both positive samples (160 valid correspondences) and negative samples (30 invalid correspondences) to evaluate whether models both...