# Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

Source: [Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data](<https://www.sota2.com/research/paper/68fa6c961e209131cea34a97>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:13:46.432Z

Authors: Dominik Stammbach, Maria Antoniak, Elliott Ash

Published: 2022-05-16T10:08:11.000Z

## Abstract

This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, villain, and victim in diverse domains: newspaper articles, movie plot summaries, and political speeches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2205.07557>)

[PDF](<https://arxiv.org/pdf/2205.07557.pdf>)