Characterizing the Investigative Methods of Fictional Detectives with Large Language Models

TL;DR

This work tackles the challenge of scalable, AI-driven characterization of fictional detective methodologies within computational narratology. It introduces a multi-LLM ensemble workflow with five phases—description generation, trait extraction, semantic grouping, consistency analysis, and reverse identification—applied to seven iconic detectives. The approach yields distinct trait profiles validated against literary analyses, achieving an overall cross-model accuracy of 91.43% (with perfect scores for several detectives and notable Dupin-Holmes overlap). The results demonstrate a robust, reproducible framework that can inform AI-driven interactive storytelling and future cross-genre narrative generation.

Abstract

Detective fiction, a genre defined by its complex narrative structures and character-driven storytelling, presents unique challenges for computational narratology, a research field focused on integrating literary theory into automated narrative generation. While traditional literary studies have offered deep insights into the methods and archetypes of fictional detectives, these analyses often focus on a limited number of characters and lack the scalability needed for the extraction of unique traits that can be used to guide narrative generation methods. In this paper, we present an AI-driven approach for systematically characterizing the investigative methods of fictional detectives. Our multi-phase workflow explores the capabilities of 15 Large Language Models (LLMs) to extract, synthesize, and validate distinctive investigative traits of fictional detectives. This approach was tested on a diverse set of seven iconic detectives - Hercule Poirot, Sherlock Holmes, William Murdoch, Columbo, Father Brown, Miss Marple, and Auguste Dupin - capturing the distinctive investigative styles that define each character. The identified traits were validated against existing literary analyses and further tested in a reverse identification phase, achieving an overall accuracy of 91.43%, demonstrating the method's effectiveness in capturing the distinctive investigative approaches of each detective. This work contributes to the broader field of computational narratology by providing a scalable framework for character analysis, with potential applications in AI-driven interactive storytelling and automated narrative generation.