/emotion_gendered_stereotypes

MIT LicenseMIT

Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution

This repository contains the data of the paper Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution published at ACL 2024. See the paper for additional details:

Plaza-del-Arco, F. M., Curry, A. C., Curry, A., Abercrombie, G., & Hovy, D. (2024). Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Link.

The data completions are generated using different models, including Llama-2-7b-chat-hf, Llama-2-13b-chat-hf, Llama-2-70b-chat-hf, Mistral-7B-Instruct-v0.1, and gpt-4.

Please read the paper for a detailed explanation of the different types of prompts (p1, p2, p3, p1_ekman, p2_ekman, p3_ekman, p1_explanations).

License

Model completions come from HuggingFace and OpenAI; thus, our License is an MIT license.

Citation

@inproceedings{plaza-del-arco-etal-2024-angry,
    title = "Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution",
    author = "{Plaza-del-Arco}, Flor Miriam  and
    Curry, Amanda  and
    Cercas Curry, Alba  and
    Abercrombie, Gavin  and
    Hovy, Dirk",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.415",
    doi = "10.18653/v1/2024.acl-long.415",
    pages = "7682--7696"
}