· 2021
Gender and Representation Bias in GPT-3 Generated Stories
- 290citations
- 2021year
Short summary
GPT-3 generated stories reflect gender stereotypes, associating feminine characters with family/appearance and describing them as less powerful than masculine characters, even when prompted with high-power verbs.
AI-generated from the title and abstract; the full text is not read.
Key points
- GPT-3 stories show gender stereotypes based on character prompts.
- Feminine characters are linked to family and appearance topics.
- Masculine characters are depicted as more powerful than feminine characters.
- Bias persists even when high-power verbs are used for feminine characters.
AI-generated from the title and abstract; the full text is not read.
Abstract
Using topic modeling and lexicon-based word similarity, we find that stories generated by GPT-3 exhibit many known gender stereotypes. Generated stories depict different topics and descriptions depending on GPT-3's perceived gender of the character in a prompt, with feminine characters 1 more likely to be associated with family and appearance, and described as less powerful than masculine characters, even when associated with high power verbs in a prompt. Our study raises questions on how one can avoid unintended social biases when using large language models for storytelling.
The authors' abstract, as published at the source., 2021 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: General Social Sciences
General Social SciencesSocial Sciences