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

要旨

We characterize and demonstrate how the principles of direct manipulation 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.

受賞
Honorable Mention
著者
Damien Masson
University of Waterloo, Waterloo, Ontario, Canada
Sylvain Malacria
Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRIStAL, Lille, France
Géry Casiez
Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189 CRIStAL, Lille, France
Daniel Vogel
University of Waterloo, Waterloo, Ontario, Canada
論文URL

https://doi.org/10.1145/3613904.3642462

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: User Studies on Large Language Models

314
5 件の発表
2024-05-13 20:00:00
2024-05-13 21:20:00