Titre :

DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models

Auteur(s) :

Masson, Damien [Auteur]
University of Toronto
Cheriton School of Computer Science [Waterloo] [CS]
Malacria, Sylvain [Auteur]
Cheriton School of Computer Science [Waterloo] [CS]
Technology and knowledge for interaction [LOKI]
Casiez, Géry [Auteur]
Institut universitaire de France [IUF]
Cheriton School of Computer Science [Waterloo] [CS]
Technology and knowledge for interaction [LOKI]
Vogel, Daniel [Auteur]
Cheriton School of Computer Science [Waterloo] [CS]

Titre de la manifestation scientifique :

Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2024)

Organisateur(s) de la manifestation scientifique :

ACM

Ville :

Honolulu

Pays :

Etats-Unis d'Amérique

Date de début de la manifestation scientifique :

2024-05-11

Mot(s)-clé(s) en anglais :

Human-centered computing → Interactive systems and tools
Interaction design theory concepts and paradigms direct manipulation large language models prompt engineering
Interaction design theory
concepts and paradigms direct manipulation
large language models
prompt engineering
Human-computer Interaction

Discipline(s) HAL :

Informatique [cs]/Interface homme-machine [cs.HC]

Résumé en anglais : [en]

We characterize and demonstrate how the principles of direct ma- nipulation can improve interaction with large language models. This includes: continuous representation of generated objects of interest; reuse of prompt ...
Lire la suite >We characterize and demonstrate how the principles of direct ma- nipulation can improve interaction with large language models. This includes: continuous representation of generated objects of interest; reuse of prompt syntax in a toolbar of commands; manipulable outputs to compose or control the effect of prompts; and undo mechanisms. This idea is exemplified in DirectGPT, a user interface layer on top of ChatGPT that works by transforming direct manipulation actions to engineered prompts. A study shows participants were 50% faster and relied on 50% fewer and 72% shorter prompts to edit text, code, and vector images compared to baseline ChatGPT. Our work contributes a validated approach to integrate LLMs into traditional software using direct manipulation. Data, code, and demo available at https://osf.io/3wt6s.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL