DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.64134 · Cited by 10,460
An Empirical Evaluation of the System Usability Scale
Bangor, A., Kortum, P. T., & Miller, J. T. (2008) · International Journal of Human–Computer Interaction · doi:10.1080/10447310802205776 · Cited by 5,181 · cited 1×
“On the System Usability Scale, and for the specific given tasks, DirectGPT was rated 92 (typically considered “Excelent” [3]) whereas ChatGPT received a 53 (typically considered “OK”).”
MethodWhy Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
Zamfirescu-Pereira, J. D., Wong, R. Y., Hartmann, B., & Yang, Q. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581388 · Cited by 1,274 · cited 7×
“An example are “do not” statements that LLMs are known to ignore, or worse, treat as “do” statements [76].”
BackgroundResultInfluentialPrompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Reynolds, L., & McDonell, K. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451760 · Cited by 952 · cited 3×
“These issues are reminiscent of the reasons why direct manipulation interfaces emerged as an alternative to command line interfaces [25, 58, 59]. to interfaces for LLMs today: (i) indirect engagement due to manipulating semantic distance due to the verbosity and difficulty to convey intent in a prompt; and (iii) artic…”
BackgroundVaithilingam, P., Zhang, T., & Glassman, E. L. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519665 · Cited by 660
Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
Lu, Y., Bartolo, M., Moore, A., Riedel, S., & Stenetorp, P. (2021) · arXiv · doi:10.48550/arxiv.2104.08786 · Cited by 615 · cited 2×
“For the latter, the revert prompt itself is saved in the history which can impact future interactions [36, 67].”
BackgroundFantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
Lu, Y., Bartolo, M., Moore, A., Riedel, S., & Stenetorp, P. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.556 · Cited by 610 · cited 2×
“For the latter, the revert prompt itself is saved in the history which can impact future interactions [36, 67].”
BackgroundDirect manipulation vs. interface agents
Shneiderman, B., & Maes, P. (1997) · Interactions · doi:10.1145/267505.267514 · Cited by 518 · cited 1×
“This work takes the perspective that both can work together to enable “increased automation that amplifies the productivity of users and gives them increased capabilities in carrying out their tasks, while preserving their sense of control and their responsibility” [24, 62].”
BackgroundWordcraft: Story Writing With Large Language Models
Yuan, A., Coenen, A., Reif, E., & Ippolito, D. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511105 · Cited by 374 · cited 1×
“Buttons have been used as shortcuts to execute predefined prompts that ask for more information about a topic [27, 65], edit a story [13, 75], and run macros to generate computer code [26].”
Method
Cited by
Writing with AI Lowers Psychological Ownership, but Longer Prompts Can Help
Joshi, N., & Vogel, D. (2025) · Proceedings of the 7th ACM Conference on Conversational User Interfaces · doi:10.1145/3719160.3736608 · Cited by 50
Self-citationXie, L., Zheng, C., Xia, H., Qu, H., & Zhu-Tian, C. (2024) · Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3654777.3676374 · Cited by 52
Nabokov's Cards: An AI Assisted Prewriting System to Support Bottom-Up Creative Writing
Carrera, D., Zhao, Z., Ajin Thomas, A., & Wigdor, D. (2025) · Proceedings of the 2025 Conference on Creativity and Cognition · doi:10.1145/3698061.3726916 · Cited by 6
Zhang, C., Zhu, S., Yang, X., Tseng, Y.-C., Jiang, S., & Rzeszotarski, J. M. (2025) · Proceedings of the 7th ACM Conference on Conversational User Interfaces · doi:10.1145/3719160.3736618 · Cited by 4
Metadata
- Authors
- Masson, D., Malacria, S., Casiez, G., & Vogel, D.
- Venue
- Proceedings of the CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2024-05-11
- Pages
- 1-16
- OpenAlex
- W4396828482
- Cited by
- 107
- References
- 31
- FWCI
- 35.41
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models. https://app.cochat.ai/papers/10.1145/3613904.3642462
- The paper
- Masson, D., Malacria, S., Casiez, G., & Vogel, D. (2024). DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models. Proceedings of the CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3613904.3642462
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.