A multi-LLM workflow extracted and synthesized distinctive investigative trait profiles for seven fictional detectives, achieving 91.43% reverse-identification accuracy across the same models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Characterizing the Investigative Methods of Fictional Detectives with Large Language Models
A multi-LLM workflow extracted and synthesized distinctive investigative trait profiles for seven fictional detectives, achieving 91.43% reverse-identification accuracy across the same models.