mlsanityData to 7 Oct 2026

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

arXiv 2205.07557 ↗First posted 16 May 2022cs.CLcited by 27

Not on the map. Why?

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.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 16 of its 40 references that are in the map. First posted on arXiv 16 May 2022.

Builds on

16 of 40 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  5. 2018Datasheets for Datasetscited by 1,371
  6. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  8. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  9. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  10. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  11. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  12. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
4 more
  1. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
  2. 2015Ask Me Anything: Dynamic Memory Networks for Natural Language Processingcited by 116
  3. 2018Framing and Agenda-setting in Russian News: a Computational Analysis of Intricate Political Strategiescited by 47
  4. 2021Uncovering Implicit Gender Bias in Narratives through Commonsense Inferencecited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 10; 2025: 5; 2026: 5.

27 papers.

Sort:

By area:

  1. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 138
  2. 2023Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4cited by 123
  3. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  4. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  5. 2024Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Workscited by 38
  6. 2023Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytellingcited by 26
  7. 2023Where Do People Tell Stories Online? Story Detection Across Online Communitiescited by 16
  8. 2024Large Language Models Fall Short: Understanding Complex Relationships in Detective Narrativescited by 14
  9. 2024Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3cited by 8
  10. 2024ReALM: Reference Resolution As Language Modelingcited by 7
  11. 2025Entity Framing and Role Portrayal in the Newscited by 6
  12. 2025Talking Point based Ideological Discourse Analysis in News Eventscited by 4
15 more
  1. 2023GPT Struct Me: Probing GPT Models on Narrative Entity Extractioncited by 3
  2. 2024Evaluating Computational Representations of Character: An Austen Character Similarity Benchmarkcited by 3
  3. 2024Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMscited by 3
  4. 2024Mapping News Narratives Using LLMs and Narrative-Structured Text Embeddingscited by 2
  5. 2024Says Who? Effective Zero-Shot Annotation of Focalizationcited by 2
  6. 2023From stage to page: language independent bootstrap measures of distinctiveness in fictional speechcited by 1
  7. 2024Recall Them All: Retrieval-Augmented Language Models for Long Object List Extraction from Long Documentscited by 1
  8. 2025Computational Narrative Understanding for Expressive Text-to-Speechcited by 1
  9. 2026S-VoCAL: A Dataset and Evaluation Framework for Inferring Speaking Voice Character Attributes in Literaturecited by 1
  10. 2026A Structured Clustering Approach for Inducing Media Narrativescited by 1
  11. 2026GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Studycited by 1
  12. 2025Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contextscited by 0
  13. 2025A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detectioncited by 0
  14. 2026Measuring Narrative Polarization in Online Discoursecited by 0
  15. 2026Uncovering Temporal Framing in the Newscited by 0