Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systems
Open accessThe DOI matches its Crossref record; 76 of the 89 references it cites were found in a registry or an index, and 4 are not checked yet; 32 of the 49 sources its claims cite were checked for support.
Abstract
AI co-writing systems challenge long held ideals about agency and ownership in the creative process, thereby hindering widespread adoption. To address this, we investigate conceptions of agency and ownership in AI creative co-writing. Drawing on insights from a review of commercial systems, we developed three co-writing systems with similar functionality but differing interface metaphors: agentic, tool-like, and magical. Through interviews with creative writers (n=18), we explored the role of these metaphors in participants’ sense of control and authorship. Our analysis resulted in a taxonomy of agency and ownership subtypes and underscored how metaphorical framings afforded participants different conceptions of agency and ownership. We conclude with recommendations for the design of AI co-writing systems, emphasizing the role of metaphors in participants’ creative practice.
Verified 2026-11-19 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
The paper investigates how interface metaphors in AI creative co-writing systems shape writers’ conceptions of agency and ownership. Through a review of 12 commercial systems and interviews with 18 writers using three prototype metaphors, it identifies three agency subtypes and three ownership subtypes, arguing that metaphors frame expectations of control and authorship.
Key findings
- A review of 12 commercial AI creative co-writing systems identified three recurring interface metaphor archetypes: agent-like (7 systems), tool-like (10 of 12 systems), and magic-like (9 systems); sparkles appeared in 8 of 12 systems.
- Interviews with 18 writers (9 professional, 9 non-professional) produced a taxonomy of agency—explicit control, implicit control, and writing process control—and ownership—stylistic, conceptual, and effort-based.
- Tool-like metaphors shifted writers’ expected points of control toward explicit interface elements such as dropdowns, sliders, and buttons, even though those parameters did not actually modify the AI output; some participants noticed this and felt less control (e.g., P17).
- Agent-like metaphors foregrounded conceptual contributions: participants attributed ownership to ideas, plot points, character sketches, and setting, even though the system was only capable of generating more text.
Methods
- In May 2024, the authors reviewed commercial AI co-writing systems: a preliminary search found 45 systems, non-creative-writing systems were excluded, and 12 were reviewed in depth (ChatGPT, DreamGen, Fictionary, Google Gemini in Google Docs, Grammarly, NovelAI, NovelCraft, Novelcrafter, Quillbot, Squibler, Sudowrite, and Writesonic), with hour-long explorations of each.
- Three prototype systems with near-identical functionality were built: Wordsworth (agent-like), Autowrite (tool-like), and Magic Quill (magic-like). Completions used GPT-3.5-turbo, limited to 250 tokens (approximately 100 words).
- The exploratory study used a between-subjects design: 18 participants (9 professional creative writers, 9 non-professional writers) completed a 15-minute writing task with one randomly assigned prototype, followed by semi-structured interviews; sessions lasted 60–90 minutes. Analysis used open coding followed by reflexive thematic analysis by two coders, with professional and non-professional themes initially analyzed separately and then merged.
Limitations
- Stated: the review focused on commercial systems available at the time, and new systems may introduce new metaphors; longitudinal studies of a week or more may provide more reliable results; findings may be culturally specific to North American, English-language creative writers, so future work is needed in other cultures, languages, and genres.
- Evident from the text: the prototypes used deception to maintain identical functionality—Autowrite’s sliders and dropdowns did not modify AI output, and Wordsworth’s chat responses were scripted—so participants’ expectations of control were tested against non-functional controls.
- Evident from the text: the study used a short 15-minute writing task, a small sample of 18 participants, and a between-subjects design, which limits generalizability and prevents within-participant comparison of metaphors.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures



Verification
Claims the paper makes
25 Valid · 2 Not valid · 10 Not checked · 59 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To support broader adoption of AI co-writing systems among writers, it is crucial to consider perceived agency and perceived ownership, as these factors can influence a writer's long-term satisfaction with such systems [23].”
What the sources say
- Partly supportedcites [23] [23] Katy Ilonka Gero, Tao Long, and Lydia B Chilton. 2023. Social Dynamics of AI Support in Creative Writing. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 245, 15 pages. https://doi.org/10.1145/3544548.3580782 - sourceExperimental — accuracy not yet measured
Section 4.4.1 describes writers’ authority to accept or reject suggestions, and Section 5.2.3 discusses ownership and authenticity in AI-assisted writing. But Section 7.1 says most participants had limited experience with AI writing tools; the paper does not establish that perceived agency or ownership influences long-term satisfaction with them. (LLM, conf=0.85)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Based on this review and prior literature [35], we identified three interface metaphor archetypes that were the most prevalent: tool-like, agentic, and magic.”
- Also stated in: § 3 Interface Metaphors in Commercial AI Creative Co-Writing Systems · p. 5 · plain
“Our review revealed three recurring archetypes of how AI interactions were presented to users through interface elements: Agent-like, Tool-like, and Magic-like (Table 1).”
What the sources say
- Partly supportedcites [35] [35] Mina Lee, Katy Ilonka Gero, John Joon Young Chung, Simon Buckingham Shum, Vipul Raheja, Hua Shen, Subhashini Venugopalan, Thiemo Wambsganss, David Zhou, Emad A. Alghamdi, Tal August, Avinash Bhat, Madiha Zahrah Choksi, Senjuti Dutta, Jin L.C. Guo, Md Naimul Hoque, Yewon Kim, Simon Knight, Seyed Parsa Neshaei, Antonette Shibani, Disha Shrivastava, Lila Shroff, Agnia Sergeyuk, Jessi Stark, Sarah Sterman, Sitong Wang, Antoine Bosselut, Daniel Buschek, Joseph Chee Chang, Sherol Chen, Max Kreminski, Joonsuk Park, Roy Pea, Eugenia Ha Rim Rho, Zejiang Shen, and Pao Siangliulue. 2024. A Design Sp sourceExperimental — accuracy not yet measured
The “UI -Interaction Metaphor” section identifies agent and tool metaphors, but its third primary metaphor is hybrid, not magic. The passage also does not establish that the three claimed archetypes are the most prevalent in commercial systems. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3 Interface Metaphors in Commercial AI Creative Co-Writing Systems · p. 5 · plain
Every source the paper cites for this claim was checked and supports it.
In the paper
“Participants were more likely to claim authorship of AI-assisted texts than human-assisted ones.”
What the sources say
- Supportedcites [19] [19] Fiona Draxler, Anna Werner, Florian Lehmann, Matthias Hoppe, Albrecht Schmidt, Daniel Buschek, and Robin Welsch. 2024. The AI Ghostwriter Effect: When Users do not Perceive Ownership of AI-Generated Text but Self-Declare as Authors. ACM Trans. Comput.-Hum. Interact. 31, 2, Article 25 (feb 2024), 40 pages. https://doi.org/10.1145/3637875 - source
In Study 2, the H5: Differences in Authorship Declaration section reports that participants named the AI as an author significantly less often than they named the human ghostwriter, Sasha, or another entity besides themselves. This supports the comparison that participants were more likely to claim authorship of AI-assisted texts. The passage does not specify whether they claimed sole or shared authorship. (LLM, conf=0.88)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Comparative research on metaphors for AI has demonstrated the impact metaphors can have on user interactions with task-based AI systems, e.g., AI that assists with well-defined tasks such as travel planning [32] or waste sorting [46].”
What the sources say
- Supportedcites [32] [32] Pranav Khadpe, Ranjay Krishna, Li Fei-Fei, Jeffrey T. Hancock, and Michael S. Bernstein. 2020. Conceptual Metaphors Impact Perceptions of Human-AI Collaboration. Proc. ACM Hum.-Comput. Interact. 4, CSCW2, Article 163 (oct 2020), 26 pages. https://doi.org/10.1145/3415234 - source
The Methods (p. 6) identify the study as a comparison of metaphors for a task-focused conversational agent, using a travel-planning task. The Conclusion (p. 22) reports that metaphor choices changed users’ evaluations, intentions to adopt, and desire to cooperate with the agent. (LLM, conf=0.93)
- Not checked — no full text of the sourcecites [46] [46] Eleftherios Papachristos, Patrick Skov Johansen, Rune Møberg Jacobsen, Lukas Bjørn Leer Bysted, and Mikael B. Skov. 2021. How do People Perceive the Role of AI in Human-AI Collaboration to Solve Everyday Tasks?. In CHI Greece 2021: 1st International Conference of the ACM Greek SIGCHI Chapter (Online (Athens, Greece), Greece) (CHI Greece 2021). Association for Computing Machinery, New York, NY, USA, Article 10, 6 pages. https://doi.org/10.1145/3489410.3489420 - source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Magic-like interfaces , present in nine systems, did not fall along the Tool-Hybrid-Agent spectrum described by Lee et al. [35].”
What the sources say
- Supportedcites [35] [35] Mina Lee, Katy Ilonka Gero, John Joon Young Chung, Simon Buckingham Shum, Vipul Raheja, Hua Shen, Subhashini Venugopalan, Thiemo Wambsganss, David Zhou, Emad A. Alghamdi, Tal August, Avinash Bhat, Madiha Zahrah Choksi, Senjuti Dutta, Jin L.C. Guo, Md Naimul Hoque, Yewon Kim, Simon Knight, Seyed Parsa Neshaei, Antonette Shibani, Disha Shrivastava, Lila Shroff, Agnia Sergeyuk, Jessi Stark, Sarah Sterman, Sitong Wang, Antoine Bosselut, Daniel Buschek, Joseph Chee Chang, Sherol Chen, Max Kreminski, Joonsuk Park, Roy Pea, Eugenia Ha Rim Rho, Zejiang Shen, and Pao Siangliulue. 2024. A Design Sp source
The “UI -Interaction Metaphor” section describes tool and agent metaphors and says hybrid systems blend the two. That supports the Tool-Hybrid-Agent framework attributed to Lee et al.; the nine magic-like systems and their placement outside it are the citing authors’ own finding. (LLM, conf=0.92)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
39 more claims · 2 with their cited sources checked
Create a free account to see all 96 claims and every source verdict.
- It may state two separate claims as one. 22
- Probably not a substantial claim. 40
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 5.2 Interface Metaphors' Effect on Agency and Ownership · p. 14
“Participants that used the agent-like system tended to focus on the importance of ideation and conceptual contributions like plot points, character sketches, and setting as opposed to individual sentences. Some participants, like P13, argued that the agent-like system expanded on what they had previously written, stating, "I think [the generated text] is based on what I've already written down, and it doesn't spark many new ideas for me to write about." P16 echoed this sentiment”
§ 3 Interface Metaphors in Commercial AI Creative Co-Writing Systems · p. 7
“| 16 | M | Educator | Non-Professional Writer | Autowrite (Tool-like) |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 5.1 Conceptions of Agency and Ownership · p. 12
“Non-professional writers (e.g., P7, P16 tool-like system; P10 magic-like system, P11, P13 agent-like system) expressed this sentiment”
§ 3 Interface Metaphors in Commercial AI Creative Co-Writing Systems · p. 7
“| 7 | F | PR Consultant | Non-Professional Writer | Magic Quill (Magic-like) |”
Citations
Cites
Clarke, V., & Braun, V. (2017) · The Journal of Positive Psychology · doi:10.1080/17439760.2016.1262613 · Cited by 6,543 · cited 1×
“Following this initial coding, we conducted a reflexive thematic analysis, as described by Braun and Clarke [15], to develop and refine themes from the coded data.”
Awareness and coordination in shared workspaces
Dourish, P., & Bellotti, V. (1992) · Proceedings of the 1992 ACM conference on Computer-supported cooperative work - CSCW '92 · doi:10.1145/143457.143468 · Cited by 2,550 · cited 1×
“The conception of control as implicit echoes previous HCI findings on collaborative writing that noted how writers implicitly provided context and direction to each other while collaborating [19].”
The State of Psychological Ownership: Integrating and Extending a Century of Research
Pierce, J. L., Kostova, T., & Dirks, K. T. (2003) · Review of General Psychology · doi:10.1037/1089-2680.7.1.84 · Cited by 2,038 · cited 1×
“These findings also suggest that Pierce et al.’s theory of psychological ownership [55] holds for AI co-writing.”
Barthes, R. (2019) · Authorship · doi:10.1515/9781474465519-017 · Cited by 1,419
The IKEA effect: When labor leads to love
Norton, M. I., Mochon, D., & Ariely, D. (2012) · Journal of Consumer Psychology · doi:10.1016/j.jcps.2011.08.002 · Cited by 1,049 · cited 1×
“Energy and labor investment directly aligns with our findings on effort-based ownership and corroborates established research on the IKEA effect [48] (i.e., labor investment fosters a sense of ownership).”
Computation and Human Experience
Agre, P. E. (1997) · Cambridge University Press eBooks · doi:10.1017/cbo9780511571169 · Cited by 527
Wordcraft: 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
Lee, M., Liang, P., & Yang, Q. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502030 · Cited by 345
Interface Metaphors and User Interface Design
Carroll, J. M., Mack, R. L., & Kellogg, W. A. (1988) · Handbook of Human-Computer Interaction · doi:10.1016/b978-0-444-70536-5.50008-7 · Cited by 345 · cited 1×
“We then created three AI co-writing systems, each with an interface feature that exemplified each metaphor.”
Draxler, F., Werner, A., Lehmann, F., Hoppe, M., Schmidt, A., Buschek, D., & Welsch, R. (2023) · arXiv · doi:10.48550/arxiv.2303.03283 · Cited by 284
Mirowski, P., Mathewson, K. W., Pittman, J., & Evans, R. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581225 · Cited by 240 · cited 2×
“Others used tool-like interfaces that were not found in the commercial systems, such as a tool for the generation of stories containing target words for language learning [54], and hierarchical generation [46].”
Do We Trust in AI? Role of Anthropomorphism and Intelligence
Troshani, I., Rao Hill, S., Sherman, C., & Arthur, D. (2021) · Journal of Computer Information Systems · doi:10.1080/08874417.2020.1788473 · Cited by 228 · cited 1×
“This may have been due to the AI agents not only being conceptualized as capable of providing suggestions or editing the text, but also receiving higher-order suggestions and conversing about the text conceptually with human-like nuance [72].”
Draxler, F., Werner, A., Lehmann, F., Hoppe, M., Schmidt, A., Buschek, D., & Welsch, R. (2024) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3637875 · Cited by 186 · cited 4×
“Previous work has characterized the types of ownership that matter to writers [59] and demonstrated that agency and ownership are generally correlated: writers who feel greater control while AI co-writing generally feel greater ownership over the results [20].”
InfluentialConceptual Metaphors Impact Perceptions of Human-AI Collaboration
Khadpe, P., Krishna, R., Fei-Fei, L., Hancock, J. T., & Bernstein, M. S. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415234 · Cited by 183 · cited 2×
“Comparative research on metaphors for AI has demonstrated the impact metaphors can have on user interactions with task-based AI systems, e.g., AI that assists with well-defined tasks such as travel planning [36] or waste sorting [52].”
Sparks: Inspiration for Science Writing using Language Models
Gero, K. I., Liu, V., & Chilton, L. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533533 · Cited by 161
Suh, S., Chen, M., Min, B., Li, T. J.-J., & Xia, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642400 · Cited by 148 · cited 1×
“Many interfaces resembled commercial instantiations of this archetype, utilizing buttons, dropdown menus, and keywords (in creative writing [51, 58, 70, 80] and other writing contexts [28, 38, 63]).”
Metaphoria: An Algorithmic Companion for Metaphor Creation
Gero, K. I., & Chilton, L. B. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300526 · Cited by 146 · cited 2×
“Early work on understanding AI co-writing in creative contexts suggested that AI involvement may decrease writers’ sense of ownership [24, 25].”
ArgueTutor: An Adaptive Dialog-Based Learning System for Argumentation Skills
Wambsganss, T., Kueng, T., Soellner, M., & Leimeister, J. M. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445781 · Cited by 138 · cited 1×
“…interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial systems.”
Revisiting Reflection in HCI: Four Design Resources for Technologies that Support Reflection
Bentvelzen, M., Woźniak, P. W., Herbes, P. S. F., Stefanidi, E., & Niess, J. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3517233 · Cited by 137
A Design Space for Intelligent and Interactive Writing Assistants
Lee, M., Gero, K. I., Chung, J. J. Y., Shum, S. B., Raheja, V., Shen, H., Venugopalan, S., Wambsganss, T., Zhou, D., Alghamdi, E. A., et al. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642697 · Cited by 136
Art or Artifice? Large Language Models and the False Promise of Creativity
Chakrabarty, T., Laban, P., Agarwal, D., Muresan, S., & Wu, C.-S. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642731 · Cited by 135
Social Dynamics of AI Support in Creative Writing
Gero, K. I., Long, T., & Chilton, L. B. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580782 · Cited by 129 · cited 4×
“Two of the ways in which writers perceive their interactions with AI co-writing systems are through their perceptions of agency when they use a system and their perceptions of ownership over the final writing product [26].”
InfluentialWhere to Hide a Stolen Elephant: Leaps in Creative Writing with Multimodal Machine Intelligence
Singh, N., Bernal, G., Savchenko, D., & Glassman, E. L. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3511599 · Cited by 119
Biermann, O. C., Ma, N. F., & Yoon, D. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533506 · Cited by 116 · cited 1×
“In addition, Biermann et al. used a design workbook approach to compare different AI interfaces and investigate how writers’ personal values affected their intent to adopt AI in their practices [6].”
Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models
Dhillon, P. S., Molaei, S., Li, J., Golub, M., Zheng, S., & Robert, L. P. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642134 · Cited by 111 · cited 1×
“Others have found that AI assistance for idea generation decreases feelings of ownership [29] and that suggesting paragraphs of text may increase writing quality but at the cost of decreased feelings of ownership [18].”
Wan, Q., Hu, S., Zhang, Y., Wang, P., Wen, B., & Lu, Z. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637361 · Cited by 88
Creative Help: A Story Writing Assistant
Roemmele, M., & Gordon, A. S. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-27036-4_8 · Cited by 83 · cited 1×
“Early work in Computer Science by Roemmele presented an AI co-writing sys-tem for writers that generated suggestions for the next sentences in a story using information retrieval techniques [61].”
Qin, H. X., Jin, S., Gao, Z., Fan, M., & Hui, P. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642105 · Cited by 82 · cited 2×
“…at creative writing, there has been research on new techniques to support story writing [33, 80], playwriting [46], character development [56], prewriting [75], non-linear story writing (also known as ‘multiverse’) [27], worldbuilding [14], cartoon-captioning [35], and feedback…”
Peng, Z., Guo, Q., Tsang, K. W., & Ma, X. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376695 · Cited by 81 · cited 1×
“…interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial systems.”
Kim, T., Shin, D., Kim, Y.-H., & Hong, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642693 · Cited by 75 · cited 1×
“Many interfaces resembled commercial instantiations of this archetype, utilizing buttons, dropdown menus, and keywords (in creative writing [51, 58, 70, 80] and other writing contexts [28, 38, 63]).”
Osone, H., Lu, J.-L., & Ochiai, Y. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3450391 · Cited by 74 · cited 1×
“Many interfaces resembled commercial instantiations of this archetype, utilizing buttons, dropdown menus, and keywords (in creative writing [51, 58, 70, 80] and other writing contexts [28, 38, 63]).”
LaMPost: Design and Evaluation of an AI-assisted Email Writing Prototype for Adults with Dyslexia
Goodman, S. M., Buehler, E., Clary, P., Coenen, A., Donsbach, A., Horne, T. N., Lahav, M., MacDonald, R., Michaels, R. B., Narayanan, A., et al. (2022) · Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3517428.3544819 · Cited by 71 · cited 1×
“Many interfaces resembled commercial instantiations of this archetype, utilizing buttons, dropdown menus, and keywords (in creative writing [51, 58, 70, 80] and other writing contexts [28, 38, 63]).”
In search of metaphors for tangible user intefaces
Svanæs, D., & Verplank, W. L. (2000) · Designing Augmented Reality Environments (DARE) · doi:10.1145/354666.354679 · Cited by 70
Writer-Defined AI Personas for On-Demand Feedback Generation
Benharrak, K., Zindulka, T., Lehmann, F., Heuer, H., & Buschek, D. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642406 · Cited by 63 · cited 1×
“…at creative writing, there has been research on new techniques to support story writing [33, 80], playwriting [46], character development [56], prewriting [75], non-linear story writing (also known as ‘multiverse’) [27], worldbuilding [14], cartoon-captioning [35], and feedback generation [4].”
Writing Stories with Help from Recurrent Neural Networks
Roemmele, M. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.9810 · Cited by 59 · cited 1×
“Later work by Roemmele and Gordon extended this system to use neural networks [60].”
Kobiella, C., Flores López, Y. S., Waltenberger, F., Draxler, F., & Schmidt, A. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641964 · Cited by 57
(Un)making AI Magic: A Design Taxonomy
Lupetti, M. L., & Murray-Rust, D. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641954 · Cited by 57
Patchview: LLM-powered Worldbuilding with Generative Dust and Magnet Visualization
Chung, J. J. Y., & Kreminski, M. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676352 · Cited by 57
A Redhead Walks into a Bar: Experiences of Writing Fiction with Artificial Intelligence
Ghajargar, M., Bardzell, J., & Lagerkvist, L. (2022) · Proceedings of the 25th International Academic Mindtrek Conference · doi:10.1145/3569219.3569418 · Cited by 54 · cited 1×
“…at creative writing, there has been research on new techniques to support story writing [33, 80], playwriting [46], character development [56], prewriting [75], non-linear story writing (also known as ‘multiverse’) [27], worldbuilding [14], cartoon-captioning [35], and feedback generation [4].”
Reza, M., Laundry, N. M., Musabirov, I., Dushniku, P., Yu, Z. Y. “., Mittal, K., Grossman, T., Liut, M., Kuzminykh, A., & Williams, J. J. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641899 · Cited by 52
Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers
Ippolito, D., Yuan, A., Coenen, A., & Burnam, S. (2022) · arXiv · doi:10.48550/arxiv.2211.05030 · Cited by 52 · cited 1×
“Looking specifically at creative writing, there has been research on new techniques to support story writing [33, 80], playwriting [46], character development [56], prewriting [75], non-linear story writing (also known as ‘multiverse’) [27], worldbuilding [14], cartoon-captioning [35], and feedback…”
Collaborative Storytelling with Large-scale Neural Language Models
Nichols, E., Gao, L., & Gomez, R. (2020) · Motion, Interaction and Games · doi:10.1145/3424636.3426903 · Cited by 50 · cited 1×
“Agent-like interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial…”
Hoque, M. N., Mashiat, T., Ghai, B., Shelton, C. D., Chevalier, F., Kraus, K., & Elmqvist, N. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641895 · Cited by 48
Metaphors in Voice User Interfaces: A Slippery Fish
Desai, S., & Twidale, M. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3609326 · Cited by 42
Shen, H., Huang, C.-Y., Wu, T., & Huang, T.-H. K. (2023) · Computer Supported Cooperative Work and Social Computing · doi:10.1145/3584931.3607492 · Cited by 42
Schmitt, O., & Buschek, D. (2021) · Creativity and Cognition · doi:10.1145/3450741.3465253 · Cited by 41 · cited 1×
“Agent-like interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial…”
Enhancing User Experience Through Customisation of UI Design
Hui, S. L. T., & See, S. L. (2015) · Procedia Manufacturing · doi:10.1016/j.promfg.2015.07.237 · Cited by 40 · cited 2×
“NovelCraft [49] reinforced magical framing through wand iconography, while sparkles (which have been found to contribute to the perception of magic [32]) appeared in 8 of the 12 systems.”
Shneiderman, B. (1981) · ACM SIGSOC Bulletin · doi:10.1145/1015579.810991 · Cited by 40
Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
Reza, M., Thomas-Mitchell, J., Dushniku, P., Laundry, N., Williams, J. J., & Kuzminykh, A. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757566 · Cited by 37 · cited 4×
“Reza et al. recently identified a distinction be-tween academic and creative writers’ values in ownership, finding that academic writers valued the ideas and content of pieces they created, while creative writers valued the formal and linguistic elements [59].”
InfluentialSelf-citationGuo, A., Pataranutaporn, P., & Maes, P. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650892 · Cited by 32
The Spheres of Control scale: the identification of a clear replicable three-factor structure
Spittal, M. J., Siegert, R. J., McClure, J., et al. (2002) · Personality and Individual Differences · doi:10.1016/s0191-8869(01)00010-1 · Cited by 31
Li, Q., & Luximon, Y. (2023) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2022.2050540 · Cited by 30
Sharples, M., & y Pérez, R. P. (2022) · Routledge eBooks · doi:10.4324/9781003161431 · Cited by 29
Deception and magic in collaborative interaction
Marshall, J., Benford, S., & Pridmore, T. (2010) · ACM SIGCHI Conference on Human Factors in Computing Systems (CHI) · doi:10.1145/1753326.1753410 · Cited by 28
Chin, J., Desai, S., Lin, S. (.-H., & Mejia, S. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637365 · Cited by 27
Storyfier: Exploring Vocabulary Learning Support with Text Generation Models
Peng, Z., Wang, X., Han, Q., Zhu, J., Ma, X., & Qu, H. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606786 · Cited by 27 · cited 1×
“Others used tool-like interfaces that were not found in the commercial systems, such as a tool for the generation of stories containing target words for language learning [54], and hierarchical generation [46].”
The Role of Inclusion, Control, and Ownership in Workplace AI-Mediated Communication
Kadoma, K., Aubin Le Quere, M., Fu, X. J., Munsch, C., Metaxa, D., & Naaman, M. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642650 · Cited by 24 · cited 1×
“For example, Kadoma et al. found that the style of AI suggested text (e.g., hesitant or assertive) can impact writers’ perceptions of ownership [34].”
Examining Humanness as a Metaphor to Design Voice User Interfaces
Desai, S., Dubiel, M., & Leiva, L. A. (2024) · ACM Conversational User Interfaces 2024 · doi:10.1145/3640794.3665535 · Cited by 21
Authors' Values and Attitudes Towards AI-bridged Scalable Personalization of Creative Language Arts
Kim, T., Han, H., Adar, E., Kay, M., & Chung, J. J. Y. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642529 · Cited by 20 · cited 1×
“Gero et al. reported on how writers reasoned about AI support differently than human support [26] and Kim et al. identified the benefits of AI co-writing based on the dynamics between an author, artifact, and the audience [37].”
Magic Camera: An AI Drawing Game Supporting Instantaneous Story Creation for Children
Zhao, Y., Cheng, Y., Ding, S., Yan, F., Cao, W., Liu, K., & Cao, J. (2024) · ACM International Conference on Interaction Design and Children (IDC) · doi:10.1145/3628516.3659386 · Cited by 16 · cited 2×
“We observed the application of magic metaphors in multiple VR and visual art co-creative AI systems [23, 30, 79, 81].”
How do People Perceive the Role of AI in Human-AI Collaboration to Solve Everyday Tasks?
Papachristos, E., Skov Johansen, P., Møberg Jacobsen, R., Bjørn Leer Bysted, L., & Skov, M. B. (2021) · CHI Greece 2021: 1st International Conference of the ACM Greek SIGCHI Chapter · doi:10.1145/3489410.3489420 · Cited by 15 · cited 2×
“Comparative research on metaphors for AI has demonstrated the impact metaphors can have on user interactions with task-based AI systems, e.g., AI that assists with well-defined tasks such as travel planning [36] or waste sorting [52].”
Taiye, M., High, C., Velander, J., Matar, K., Okmanis, R., & Milrad, M. (2024) · Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing · doi:10.1145/3605098.3636055 · Cited by 14 · cited 1×
“…interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial systems.”
Kariyawasam, H., Niwarthana, A., Palmer, A., Kay, J., & Withana, A. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645161 · Cited by 9 · cited 1×
“…at creative writing, there has been research on new techniques to support story writing [33, 80], playwriting [46], character development [56], prewriting [75], non-linear story writing (also known as ‘multiverse’) [27], worldbuilding [14], cartoon-captioning [35], and feedback generation [4].”
Proceedings of the 19th Spring Conference on Computer Graphics
(2003) · doi:10.1145/984952 · Cited by 9
Stage Wizard: Enhancing Tangible Storytelling with Multimodal LLMs
Han, K., Tang, K., & Wang, M. (2025) · Proceedings of the Nineteenth International Conference on Tangible, Embedded, and Embodied Interaction · doi:10.1145/3689050.3704429 · Cited by 8 · cited 2×
“We observed the application of magic metaphors in multiple VR and visual art co-creative AI systems [23, 30, 79, 81].”
CoachGPT: A Scaffolding-based Academic Writing Assistant
Chen, F., Veng, S., Wilson, J., Li, X., & Fang, H. (2025) · Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3726302.3730143 · Cited by 6 · cited 1×
“Agent-like interfaces were also common in HCI literature on AI co-writing, in both creative writing [24, 47, 56, 62] and other writing contexts [11, 13, 53, 66, 71, 74], featuring chat interfaces with avatars, personified agents, and streaming text that was similar to the reviewed commercial…”
Supporting Novice Researchers to Write Literature Review using Language Models
Choe, K., Park, S., Jung, S., Kim, H., Yang, J. W., Hong, H., & Seo, J. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650787 · Cited by 6
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
Self-citationMagic Brush: An AI-based Service for Dementia Prevention focused on Intrinsic Motivation
Yang, M., Lee, K., Kim, E., Song, Y., Lee, S., Kang, J., Han, J., Song, H., & Kim, T.-E. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555549 · Cited by 6 · cited 1×
“We observed the application of magic metaphors in multiple VR and visual art co-creative AI systems [23, 30, 79, 81].”
Any Means Necessary to Refuse Erasure by Algorithm: Lillian-Yvonne Bertram’s Travesty Generator
Whalen, Z. (2023) · Digital humanities quarterly · doi:10.63744/nj5ge4mj39t9 · Cited by 4
Examining Human-AI Collaboration for Co-Writing Constructive Comments Online
Shahid, F., Dittgen, M., Naaman, M., & Vashistha, A. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757591 · Cited by 3 · cited 1×
“Many interfaces resembled commercial instantiations of this archetype, utilizing buttons, dropdown menus, and keywords (in creative writing [51, 58, 70, 80] and other writing contexts [28, 38, 63]).”
Garnier, P.-H. (2023) · Proceedings of the 2023 ACM International Conference on Interactive Media Experiences Workshops · doi:10.1145/3604321.3604381 · Cited by 1 · cited 2×
“We observed the application of magic metaphors in multiple VR and visual art co-creative AI systems [23, 30, 79, 81].”
The 'Magic Paradigm' for Programming Smart Connected Devices
Güldenpfennig, F., Dudo, D., & Purgathofer, P. (2019) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3290607.3312892 · Cited by 1
METAPHORICAL FRAMINGS IN THE NEW YORK TIMES ONLINE PRESS REPORTS ABOUT CHATGPT
N. Figar, V. (2023) · PHILOLOGIA MEDIANA · doi:10.46630/phm.15.2023.27 · Cited by 1
Ink and Individuality: Crafting a Personalised Narrative in the Age of LLMs
Wasi, A. T., Islam, R., & Islam, M. R. (2024) · arXiv · doi:10.48550/arxiv.2404.00026
Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
Reza, M., Thomas-Mitchell, J., Dushniku, P., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.12488
Self-citationLeah Asmelash. 2023. These books are being used to train AI. No one told the authors. https://www.cnn.com/2023/10/08/style/ai-books3-authors-nora-roberts-cec/index.html. [Accessed 03-09-2024].
(n.d.)
UnresolvedRoland Barthes. 2016. The death of the author. In Readings in the Theory of Religion. Routledge, 141–145.
Roland, B. (2016)
UnresolvedAlex Calderwood, Vivian Qiu, Katy Ilonka Gero, and Lydia B Chilton. 2018. How Novelists Use Generative Language Models: An Exploratory User Study. In 23rd International Conference on Intelligent User Interfaces. ACM.
Alex, C. (2018)
UnresolvedDreamGen. 2024. AI Role-Play and Story Generator | DreamGen. https://dreamgen.com/. Retrieved: 2024-06-03.
(n.d.)
UnresolvedStephen Marche. 2023. Death of an Author: AI Wrote 95 Percent of This Murder Mystery. Wired (May 15 2023). Retrieved from https://www.wired.com/story/death-of-an-author-ai-book-review/.
(n.d.)
UnresolvedAaron Marcus. 1992. Graphic Design for Electronic Documents and User Interfaces. Addison-Wesley.
Aaron, M. (1992)
UnresolvedNovelCraft. 2024. NovelCraft | AI-powered Brainstorming For Writers And Creatives. https://www.novelcraft.net/. Retrieved: 2024-05-30.
(n.d.)
UnresolvedNovelcrafter. 2024. novelcrafter - Your Novel Writing Toolbox. https://www.novelcrafter.com/. Retrieved: 2024-05-30.
(n.d.)
UnresolvedQuillbot. 2024. Quillbot: Make Writing Painless. https://quillbot.com/. Retrieved: 2024-05-31.
(n.d.)
UnresolvedPercy Bysshe Shelley. 1910. A defence of poetry. Vol. 20. TB Mosher.
Bysshe, S. P. (1910)
UnresolvedSudowrite. 2024. Sudowrite - Best AI Writing Partner for Fiction. https://www.sudowrite.com/. Retrieved: 2024-05-30.
(n.d.)
UnresolvedTristan Tzara. 2018. Seven Dada manifestos and lampisteries. Alma Books.
Tristan, T. (2018)
UnresolvedWritesonic. 2024. Writesonic - AI Content Writer AI SEO Toolkit & AI Chatbots. https://writesonic.com/. Retrieved: 2024-05-31.
(n.d.)
Unresolved
Cited by
Beyond Compliance: How AI Could Help Creative Writers by Refusing Them
Qin, H. X., Zhu, G., Fan, M., & Hui, P. (2026) · Creativity and Cognition · doi:10.1145/3803784.3807571 · Cited by 1
(2000) · Time to knit · doi:10.1145/3772318.3808939
Lee, S. W., Choi, J., Yun, Y., Jin, S., Jang, Y., Hwang, G., Park, S. W., Ban, S., & Hyun, K. H. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2739092
When “Mine” Becomes “Yours”: How AI Builds and Erodes Consumer Psychological Ownership
Kirk, C. P., Barcohana, L., Abozid, O., & Alexander, R. G. (2026) · Springer eBooks · doi:10.1007/978-3-031-75316-9_176-1
Metadata
- Authors
- Carrera, D., Thomas-Mitchell, J., & Wigdor, D.
- Affiliations
- University of Toronto (CA)
- Venue
- Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2026-04-13
- Pages
- 1-16
- OpenAlex
- W4414695472
- Cited by
- 3
- References
- 81
- Citations by year
- 2026: 3
- FWCI
- 27.60
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Keywords
- creative agency, authorship, ownership, interface metaphors, perceived control, AI-assisted writing, AI system design
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
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.