Wordcraft: Story Writing With Large Language Models
Informations
- Type:
- inproceedings
- Auteurs:
- Yuan, Ann and Coenen, Andy and Reif, Emily and Ippolito, Daphne
- Pertinence:
-
Haute
- Référence:
- Doi:
- 10.1145/3490099.3511105
- Mots-clés:
- NLP
- Url:
- https://doi.org/10.1145/3490099.3511105
- Date de publication:
- 03/2022
- Résumé:
- an editor for human-AI collaborative story writing
- Abstract:
- The latest generation of large neural language models such as GPT-3 have achieved new levels of performance on benchmarks for language understanding and generation. These models have even demonstrated an ability to perform arbitrary tasks without explicit training. In this work, we sought to learn how people might use such models in the process of creative writing. We built Wordcraft, a text editor in which users collaborate with a generative language model to write a story. We evaluated Wordcraft with a user study in which participants wrote short stories with and without the tool. Our results show that large language models enable novel co-writing experiences. For example, the language model is able to engage in open-ended conversation about the story, respond to writers’ custom requests expressed in natural language (such as ”rewrite this text to be more Dickensian”), and generate suggestions that serve to unblock writers in the creative process. Based on these results, we discuss design implications for future human-AI co-writing systems.
- Pdf:
- Lien pdf
Références
3 articles
| Titre | Type | Pertinence | Auteurs | Date Publication | Références | Citations | Actions |
|---|---|---|---|---|---|---|---|
| Storium: A dataset and evaluation platform for machine-in-the-loop story generation | article | Moyenne | Akoury, Nader and Wang, Shufan and Whiting, Josh and Hood, Stephen and Peng, Nanyun and Iyyer, Mohit | 08/2020 | 0 | 1 | |
| Hierarchical neural story generation | article | Haute | Fan, Angela and Lewis, Mike and Dauphin, Yann | 12/2017 | 0 | 1 | |
| Attention is all you need | article | Haute | Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez,... | 12/2016 | 0 | 2 |
Citations
6 articles
| Titre | Type | Pertinence | Auteurs | Date Publication | Références | Citations | Actions |
|---|---|---|---|---|---|---|---|
| Mixed-Initiative Interaction with Computational Generative Systems | inproceedings | Lehmann, Florian | 04/2023 | 1 | 0 | ||
| Co-Writing with Opinionated Language Models Affects Users’ Views | inproceedings | Haute | Jakesch, Maurice and Bhat, Advait and Buschek, Daniel and Zalmanson, Lior and Naaman, Mor | 04/2023 | 4 | 0 | |
| Writing with (Digital) Scissors: Designing a Text Editing Tool for Assisted Storytelling Using Crowd... | inproceedings | Haute | Bala, Pauloand James, Stuartand Del Bue, Alessioand Nisi, Valentina | 12/2022 | 1 | 0 | |
| Choice Over Control: How Users Write with Large Language Models Using Diegetic and Non-Diegetic Prom... | inproceedings | Dang, Hai and Goller, Sven and Lehmann, Florian and Buschek, Daniel | 12/2022 | 1 | 0 | ||
| Design Implications of Generative AI Systems for Visual Storytelling for Young Learners | inproceedings | Moyenne | Han, Ariel and Cai, Zhenyao | 12/2022 | 1 | 0 | |
| Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries | inproceedings | Haute | Dang, Hai and Benharrak, Karim and Lehmann, Florian and Buschek, Daniel | 10/2022 | 1 | 0 |
Mots-clés
1 mots-clés
| Nom | Nombre d'articles | Actions |
|---|---|---|
| NLP | 1 |