Choice Over Control: How Users Write with Large Language Models Using Diegetic and Non-Diegetic Prom...
Informations
Type:
inproceedings
Auteurs:
Dang, Hai and Goller, Sven and Lehmann, Florian and Buschek, Daniel
Pertinence:
Référence:
Doi:
10.1145/3544548.3580969
Mots-clés:
Human-AI collaboration, Large Language Models, User-centric natural language generation, Co-creative...
Url:
https://doi.org/10.1145/3544548.3580969
Date de publication:
12/2022
Résumé:
Abstract:
We propose a conceptual perspective on prompts for Large Language Models (LLMs) that distinguishes between (1) diegetic prompts (part of the narrative, e.g. “Once upon a time, I saw a fox...”), and (2) non-diegetic prompts (external, e.g. “Write about the adventures of the fox.”). With this lens, we study how 129 crowd workers on Prolific write short texts with different user interfaces (1 vs 3 suggestions, with/out non-diegetic prompts; implemented with GPT-3): When the interface offered multiple suggestions and provided an option for non-diegetic prompting, participants preferred choosing from multiple suggestions over controlling them via non-diegetic prompts. When participants provided non-diegetic prompts it was to ask for inspiration, topics or facts. Single suggestions in particular were guided both with diegetic and non-diegetic information. This work informs human-AI interaction with generative models by revealing that (1) writing non-diegetic prompts requires effort, (2) people combine diegetic and non-diegetic prompting, and (3) they use their draft (i.e. diegetic information) and suggestion timing to strategically guide LLMs.
Références
1 articles
Titre Type Pertinence Auteurs Date Publication Références Citations Actions
Wordcraft: Story Writing With Large Language Models inproceedings Haute Yuan, Ann and Coenen, Andy and Reif, Emily and Ippolito, Daphne 03/2022 3 6
Citations
0 articles
Titre Type Pertinence Auteurs Date Publication Références Citations Actions
Pas encore d'article
Mots-clés
4 mots-clés
Nom Nombre d'articles Actions
Large Language Models 6
Human-AI collaboration 1
Co-creative systems 1
User-centric natural language generation 1
Auteurs
5 auteurs
Nom Nombre d'articles Actions
Daniel 2
Dang 2
Florian and Buschek 2
Hai and Goller 1
Sven and Lehmann 1