Automated Assistance for Creative Writing with an RNN Language Model
Open accessAbstract
This work demonstrates an interface, Creative Help, that assists people with creative writing by automatically suggesting new sentences in a story. Authors can freely edit the generated suggestions, and the application tracks their modifications. We make use of a Recurrent Neural Network language model to generate suggestions in a simple probabilistic way. Motivated by the theorized role of unpredictability in creativity, we vary the degree of randomness in the probability distribution used to generate the sentences, and find that authors' interactions with the suggestions are influenced by this randomness.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Logging interactions and analyzing them afterward can cover relatively diverse contexts across tasks and writers while allowing fine-grained analysis.
“Although this approach may provide less rich insights than interviews, it can cover relatively diverse contexts across tasks and writers, while allowing for a fne-grained analysis of interactions.”
From CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities (2022) · cites this paper as [48]
The Experiment and Results section (page unavailable) reports 139 writers, 940 suggestion–modification pairs, and an edit-distance analysis, supporting fine-grained analysis across writers. Participants wrote stories on any topic, but all performed the same story-writing task; the paper does not establish coverage across different tasks or compare interaction logs with interviews. (LLM, conf=0.86)
Experimental — accuracy not yet measuredPervasive use of AI risks eroding writers' creative autonomy and storytelling skills and might lead to over-dependence on AI-generated outputs.
“the pervasive use of AI risks eroding writers' creative autonomy and storytelling skills and might lead to an over-dependence on AI-generated outputs”
From Fanfiction in the Age of AI: Community Perspectives on Creativity, Authenticity and Adoption (2026) · cites this paper as Roemmele & Gordon, 2018
The Introduction describes AI-generated sentences as editable suggestions that may give authors new ideas. The Experiment and Results examines how authors used and edited those suggestions; the Conclusion discusses which aspects of writing such interfaces should support. None addresses whether pervasive AI use erodes creative autonomy or storytelling skills, or causes over-dependence (searched for those risks and related terms). (LLM, conf=0.75)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 5 · Cited by 55
- Authors
- Roemmele, M., & Gordon, A. S.
- Affiliations
- University of Southern California (US)
- ORCID
- Roemmele, Melissa
- Venue
- Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces
- Publisher
- ACM
- Published
- 2018-03-05
- Pages
- 1-2
- OpenAlex
- W2792969545
- Cited by
- 55
- References
- 5
- Citations by year
- 2026: 2 · 2025: 13 · 2024: 13 · 2023: 6 · 2022: 8 · 2021: 7 · 2020: 1 · 2019: 3 · 2018: 2
- FWCI
- 1.32
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM International Conference on Intelligent User Interfaces (IUI) (publishedVersion)
- Funders
- Army Research Office (W911NF-14-D-0005-0001)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- creative writing, recurrent neural network language models, story generation
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
