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

arXiv: https://arxiv.org/abs/2205.07557 · HTML: https://mlsanity.com/paper/2205.07557/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 16 May 2022.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Ask Me Anything: Dynamic Memory Networks for Natural Language Processing](https://mlsanity.com/paper/1506.07285/) (2015)
- [Framing and Agenda-setting in Russian News: a Computational Analysis of Intricate Political Strategies](https://mlsanity.com/paper/1808.09386/) (2018)
- [Uncovering Implicit Gender Bias in Narratives through Commonsense Inference](https://mlsanity.com/paper/2109.06437/) (2021)

## Built on by (most cited first, 27 of 27)

- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4](https://mlsanity.com/paper/2310.12321/) (2023)
- [Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works](https://mlsanity.com/paper/2404.12726/) (2024)
- [Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling](https://mlsanity.com/paper/2310.12902/) (2023)
- [Where Do People Tell Stories Online? Story Detection Across Online Communities](https://mlsanity.com/paper/2311.09675/) (2023)
- [Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives](https://mlsanity.com/paper/2402.11051/) (2024)
- [Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3](https://mlsanity.com/paper/2406.11380/) (2024)
- [ReALM: Reference Resolution As Language Modeling](https://mlsanity.com/paper/2403.20329/) (2024)
- [Entity Framing and Role Portrayal in the News](https://mlsanity.com/paper/2502.14718/) (2025)
- [Talking Point based Ideological Discourse Analysis in News Events](https://mlsanity.com/paper/2504.07400/) (2025)
- [GPT Struct Me: Probing GPT Models on Narrative Entity Extraction](https://mlsanity.com/paper/2311.14583/) (2023)
- [Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark](https://mlsanity.com/paper/2408.16131/) (2024)
- [Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs](https://mlsanity.com/paper/2412.04576/) (2024)
- [Mapping News Narratives Using LLMs and Narrative-Structured Text Embeddings](https://mlsanity.com/paper/2409.06540/) (2024)
- [Says Who? Effective Zero-Shot Annotation of Focalization](https://mlsanity.com/paper/2409.11390/) (2024)
- [From stage to page: language independent bootstrap measures of distinctiveness in fictional speech](https://mlsanity.com/paper/2301.05659/) (2023)
- [Recall Them All: Retrieval-Augmented Language Models for Long Object List Extraction from Long Documents](https://mlsanity.com/paper/2405.02732/) (2024)
- [Computational Narrative Understanding for Expressive Text-to-Speech](https://mlsanity.com/paper/2509.04072/) (2025)
- [S-VoCAL: A Dataset and Evaluation Framework for Inferring Speaking Voice Character Attributes in Literature](https://mlsanity.com/paper/2603.00958/) (2026)
- [A Structured Clustering Approach for Inducing Media Narratives](https://mlsanity.com/paper/2604.10368/) (2026)
- [GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study](https://mlsanity.com/paper/2605.28643/) (2026)
- [Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts](https://mlsanity.com/paper/2510.14351/) (2025)
- [A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection](https://mlsanity.com/paper/2510.21679/) (2025)
- [Measuring Narrative Polarization in Online Discourse](https://mlsanity.com/paper/2601.07398/) (2026)
- [Uncovering Temporal Framing in the News](https://mlsanity.com/paper/2606.00294/) (2026)

## Abstract (arXiv)

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.