Characterizing the Investigative Methods of Fictional Detectives with Large Language Models

2025-05-12

AI Summary

Traditional literary studies of fictional detectives suffer from narrow analytical scope and poor scalability in investigating detective reasoning methodologies. Method: This paper introduces the first verifiable and reproducible LLM-driven feature characterization framework. It employs a multi-stage workflow—including iterative prompt engineering across 15 large language models, cross-model feature extraction and fusion, human-in-the-loop validation, and reverse identification evaluation—to systematically model the inferential paradigms of seven canonical detectives. Contribution/Results: The framework enables reverse character identification and cross-text stylistic modeling, achieving 91.43% accuracy on the seven-detective classification task. Its extracted features align closely with authoritative literary scholarship. By integrating computational rigor with interpretability, the framework establishes a scalable, explainable, and automated analytical infrastructure for computational narratology.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Analyzing fictional detectives' methods using LLMs
• Scaling character trait extraction for narrative generation
• Validating AI-driven detective style identification accuracy

Innovation

• AI-driven approach for detective method analysis
• Multi-phase LLM workflow for trait extraction
• Scalable framework validated with 91.43% accuracy