DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909504588742656 |
|---|---|
| author | Masson, Damien Malacria, Sylvain Casiez, Géry Vogel, Daniel |
| author_facet | Masson, Damien Malacria, Sylvain Casiez, Géry Vogel, Daniel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_03691 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models Masson, Damien Malacria, Sylvain Casiez, Géry Vogel, Daniel Human-Computer Interaction 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. |
| title | DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2310.03691 |