Literary characters and GPT-4: from William Shakespeare to Elena Ferrante.
We prompted GPT-4 (a large language model) to play the Dictator game, a classic behavioral economics experiment, as 148 literary fictional characters from the 17th century to the 21st century. There is a general and mainly monotonic decrease in selfish behavior over time in literary characters. Fift...
| Publicado en: | Digital Scholarship in the Humanities Vol. 40; no. 1; pp. 1 - 15 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Oxford University Press / USA
Apr2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=184296826&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 184296826 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 2055768X JEO9 jtl: Digital Scholarship in the Humanities issn: 2055768X maglogo: N pubinfo: dt: Apr2025 vid: 40 iid: 1 pid: 622 pub: Oxford University Press / USA artinfo: ui: 184296826 10.1093/llc/fqae079 ppf: 1 ppct: 14 formats: fmt: – @attributes: type: T – @attributes: type: P size: 954KB tig: atl: Literary characters and GPT-4: from William Shakespeare to Elena Ferrante. aug: au: Abrams, Gabriel affil: Sidwell Friends High School, Washington, DC 20016, United States su: Language models Literary characters Generative pre-trained transformers History of economics Elasticity (Economics) sug: subj: Language models Literary characters Generative pre-trained transformers History of economics Elasticity (Economics) keyword: behavioral economics GPT-4 history of literature large language models literature personality types ab: We prompted GPT-4 (a large language model) to play the Dictator game, a classic behavioral economics experiment, as 148 literary fictional characters from the 17th century to the 21st century. There is a general and mainly monotonic decrease in selfish behavior over time in literary characters. Fifty per cent of the decisions of characters from the 17th century are selfish compared to just 19 per cent from the 21st century. Historical literary characters have a surprisingly strong net positive valence across 2,785 personality traits generated by GPT-4 (3.2× more positive than negative). However, valence varied significantly across centuries. Positive traits were 10× more common than negative in the 21st century, but just 1.8× more common in the 17th century. 'Empathetic', 'fair', and 'selfless', were the most overweight traits in the 20th century. Conversely, 'manipulative', 'ambitious', and 'ruthless' were the most overweight traits in the 17th century. Male characters were more selfish than female characters. The skew was highest in the 17th century, where selfish decisions for male and female were 62 and 20 per cent, respectively. This analysis also offers a quantifiable partial Turing test. The key human-like characteristics of the model are the zero price effect, lack of spitefulness, and altruism. However, the model does not have human sensitivity to relative ordinal position and has significantly lower price elasticity than humans. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: © 2019 EADH: The European Association for Digital Humanities. item: Digital Scholarship in the Humanities holder: Oxford University Press / USA dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|