Where to Hide a Stolen Elephant: Leaps in Creative Writing with Multimodal Machine Intelligence
Open accessThe DOI matches its Crossref record; 79 of the 79 references it cites were found in a registry or an index.
Abstract
While developing a story, novices and published writers alike have had to look outside themselves for inspiration. Language models have recently been able to generate text fluently, producing new stochastic narratives upon request. However, effectively integrating such capabilities with human cognitive faculties and creative processes remains challenging. We propose to investigate this integration with a multimodal writing support interface that offers writing suggestions textually, visually, and aurally. We conduct an extensive study that combines elicitation of prior expectations before writing, observation and semi-structured interviews during writing, and outcome evaluations after writing. Our results illustrate the individual and situational variation in machine-in-the-loop writing approaches, suggestion acceptance, and ways the system is helpful. Centrally, we report how participants perform integrative leaps , by which they do cognitive work to integrate suggestions of varying semantic relevance into their developing stories. We interpret these findings, offering modeling and design recommendations for future creative writing support technologies.
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Translating support provides preliminary drafts or helps the user to restructure their ideas in a different form (e.g., point form to prose), but encourages the user to write and integrate ideas on their own [21,122,124].”
From Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process (2025) · cites this paper as [122]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Reviewing support is delivered in qualitative form, such as suggestions or summaries [7,114,122].”
From Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process (2025) · cites this paper as [122]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Lenses can also be assembled together to view the same generation outputs through multiple representations [64,82].”
From Cells, Generators, and Lenses: Design Framework for Object-Oriented Interaction with Large Language Models (2023) · cites this paper as [82]
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
The Interpretation of Cultures
Fenn, R., & Geertz, C. (1974) · Journal for the Scientific Study of Religion · doi:10.2307/1384392 · Cited by 19,154 · cited 2×
“writing and to observe immediate reaction and, to the extent possible, raw and unmediated answers, allowed us to produce "thick description" [43], as noted earlier.”
BackgroundMethodDevelopment of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
(1988) · Advances in Psychology · doi:10.1016/s0166-4115(08)62386-9 · Cited by 15,003 · cited 1×
“"In which editor was the text that you wrote more creative?") and four items on cognitive load adapted from the NASA TLX survey [47] (e.”
MethodBaddeley, A. D., & Hitch, G. (1974) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60452-1 · Cited by 9,860
Marian, V., Blumenfeld, H. K., & Kaushanskaya, M. (2007) · Journal of Speech, Language, and Hearing Research · doi:10.1044/1092-4388(2007/067 · Cited by 1,991
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834 · cited 1×
“In parallel, models with implicitly richer knowledge bases [74] may also extend more diverse suggestions to users, inding interesting relations with aspects of their writing, and assisting them in performing contextually appropriate and creatively fulilling integrations.”
BackgroundSome observations on mental models
Norman, D. A. (1983) · Medical Entomology and Zoology · Cited by 1,549
Creative Cognition: Theory, Research, and Applications
Finke, R. A., Ward, T. B., & Smith, S. M. (1992) · The MIT Press eBooks · doi:10.7551/mitpress/7722.001.0001 · Cited by 1,433 · cited 1×
“More recent psychological approaches to studying creative writing have emphasized the role of retrieval, conceptual combination, and analogical mapping as some of the fundamental cognitive processes that explain creative cognition [35, 48, 95].”
BackgroundPaivio, A. (1990) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195066661.001.0001 · Cited by 1,149
Automatic Keyword Extraction from Individual Documents
Rose, S., Engel, D., Cramer, N., & Cowley, W. (2010) · Text Mining · doi:10.1002/9780470689646.ch1 · Cited by 1,095 · cited 1×
“Concept-based searches for media on these platforms are typically performed with keywords rather than long-form text, and so we use the RAKE algorithm for automatic keyword extraction [87] as a preprocessing step, pooling the keywords from both model outputs (plot and description).”
MethodA cognitive process theory of writing
Flower, L., & Hayes, J. R. (1981) · College Composition & Communication · doi:10.58680/ccc198115885 · Cited by 1,025 · cited 5×
“What are the underlying cognitive mechanisms by which distant suggestions are able to be meaningfully integrated into users’ existing narratives? Participants of our study were actively aware of the task environment [36]: writing a story using Editor-Red (nonhuman, AI system), a rhetorical problem (write a story given…”
BackgroundInfluentialStyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., & Lischinski, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00209 · Cited by 1,023 · cited 1×
“Such steering can be explicitly enabled [50, 53, 58], for example, by conditional modeling, or, in the absence of specialized approaches, even discovered by so-called "prompt engineering" which has been successfully used(7) by many for language-controlled visual art generation [73] with general-purpose vision+language…”
BackgroundThe cognitive underpinnings of effective teamwork: A meta-analysis.
DeChurch, L. A., & Mesmer-Magnus, J. R. (2010) · Journal of Applied Psychology · doi:10.1037/a0017328 · Cited by 1,014 · cited 1×
“In the context of human-machine collaboration, and even for human collaboration alone, a great deal of work has illuminated the importance of mental models in promoting team success [27].”
BackgroundThe equilibration of cognitive structures : the central problem of intellectual development
Piaget, J., Brown, T., & Thampy, K. J. (1985) · University of Chicago Press eBooks · Cited by 901
“Everyone wants to do the model work, not the data work”: Data Cascades in High-Stakes AI
Sambasivan, N., Kapania, S., Highfill, H., Akrong, D., Paritosh, P., & Aroyo, L. M. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445518 · Cited by 781 · cited 1×
“Mirroring calls from other domains for data-oriented rather than model-oriented progress in AI [28, 88], we argue that well-curated datasets oriented towards domain constructs can support diversity and relevance, two factors we identiied earlier as especially salient in machine contributions to creative writing work.”
BackgroundTonal Consonance and Critical Bandwidth
Plomp, R., & Levelt, W. J. M. (1965) · The Journal of the Acoustical Society of America · doi:10.1121/1.1909741 · Cited by 774 · cited 1×
“Since sounds need to be combined together, constraining the sensory dissonance [77] of each independent element helps to layer them efectively into a coherent soundscape.”
BackgroundCTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751 · cited 1×
“Such steering can be explicitly enabled [50, 53, 58], for example, by conditional modeling, or, in the absence of specialized approaches, even discovered by so-called "prompt engineering" which has been successfully used(7) by many for language-controlled visual art generation [73] with general-purpose vision+language…”
BackgroundStanford typed dependencies manual
de Marnee, M.-C., & Manning, C. D. (2010) · Cited by 717
Staying open to interpretation: engaging multiple meanings in design and evaluation
Sengers, P., & Gaver, B. (2006) · Proceedings of the 6th conference on Designing Interactive systems · doi:10.1145/1142405.1142422 · Cited by 620
Ward, T. B., Smith, S. M., & Finke, R. A. (1998) · Cambridge University Press eBooks · doi:10.1017/cbo9780511807916.012 · Cited by 548
Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance
Bansal, G., Nushi, B., Kamar, E., Lasecki, W. S., Weld, D. S., & Horvitz, E. (2019) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v7i1.5285 · Cited by 466 · cited 1×
“, for example, study mental models of AI performance in the context of human-AI teams [7].”
BackgroundMax Weber on the Methodology of the Social Sciences.
Nahrendorf, R. O., Shils, E. A., & Finch, H. A. (1949) · American Sociological Review · doi:10.2307/2086694 · Cited by 435 · cited 1×
“Following Max Weber’s distinction [96] between explanation that captures the causal sequence of actions and understanding that attends to the meaning of those actions, our research aims to analyze the interaction of the person with the AI system from the perspective of the latter (i.”
BackgroundChoi, H.-H., van Merriënboer, J. J. G., & Paas, F. (2014) · Educational Psychology Review · doi:10.1007/s10648-014-9262-6 · Cited by 413
Empath: Understanding Topic Signals in Large-Scale Text
Fast, E., Chen, B., & Bernstein, M. S. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858535 · Cited by 413
First I "like" it, then I hide it: Folk Theories of Social Feeds
Eslami, M., Karahalios, K., Sandvig, C., Vaccaro, K., Rickman, A., Hamilton, K., & Kirlik, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858494 · Cited by 375
Is Noise Always Bad? Exploring the Effects of Ambient Noise on Creative Cognition
Mehta, R., Zhu, R. (., & Cheema, A. (2012) · Journal of Consumer Research · doi:10.1086/665048 · Cited by 338
Effective sounds in complex systems: the ARKOLA simulation
Gaver, W. W., Smith, R. B., & O'Shea, T. (1991) · Proceedings of the SIGCHI conference on Human factors in computing systems Reaching through technology - CHI '91 · doi:10.1145/108844.108857 · Cited by 316
Mutual disambiguation of recognition errors in a multimodel architecture
Oviatt, S. (1999) · Proceedings of the SIGCHI conference on Human factors in computing systems the CHI is the limit - CHI '99 · doi:10.1145/302979.303163 · Cited by 315 · cited 1×
“One goal of a well-designed multimodal system is to integrate complementary input modes to create a synergistic blend, permitting each mode’s strengths to overcome weaknesses in the others and support "mutual compensation" of feedback errors [71].”
BackgroundDeVito, M. A., Gergle, D., & Birnholtz, J. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025659 · Cited by 311
Font, F., Roma, G., & Serra, X. (2013) · Proceedings of the 21st ACM international conference on Multimedia · doi:10.1145/2502081.2502245 · Cited by 298 · cited 4×
“Keywords are then extracted (using the RAKE algorithm) for use in the multimedia search queries: (C) calls to the Unsplash and Freesound APIs retrieve semantically associated image and audio content respectively, and these are sent back to the interface along with the suggestions to be presented to the user.”
MethodInfluentialWisniewski, E. J. (1997) · Psychonomic Bulletin & Review · doi:10.3758/bf03209392 · Cited by 281 · cited 1×
“Other possible mechanisms for combining distant concepts have also been described in prior literature, such as causal reasoning [54], comparison and construction [97], conceptual integration or "blending" [25, 92], and satisfying constraints like diagnosticity, plausibility, and informativeness [24].”
BackgroundCreative Writing with a Machine in the Loop: Case Studies on Slogans and Stories
Clark, E., Ross, A. S., Tan, C., Ji, Y., & Smith, N. A. (2018) · 23rd International Conference on Intelligent User Interfaces · doi:10.1145/3172944.3172983 · Cited by 257
Combining social concepts: The role of causal reasoning
Kunda, Z. (1990) · Cognitive Science · doi:10.1016/0364-0213(90)90009-l · Cited by 242 · cited 2×
“In the case of causal reasoning, the surprisingness of combinations may provoke additional and exploratory processes and thereby the production of creative ideas [54].”
BackgroundEfficient creativity: constraint-guided conceptual combination
Costello, F. (2000) · Cognitive Science · doi:10.1016/s0364-0213(00)00020-3 · Cited by 239
Folk Theories of Nanotechnologists
Rip, A. (2006) · Science as Culture · doi:10.1080/09505430601022676 · Cited by 236 · cited 1×
“Folk theories are a form of expectations that are based on some experience, but are not necessarily systematically checked [83].”
BackgroundGelman, S. A., & Legare, C. H. (2011) · Annual Review of Anthropology · doi:10.1146/annurev-anthro-081309-145822 · Cited by 232 · cited 1×
“While mental models ofer insight into cognitive representations of a system’s operation developed through experience, intuitive theories about the world structure learning, understanding, and cognition more broadly, in diverse ways despite a common psychological substrate [44].”
BackgroundA Social-Interactive Model of Writing
NYSTRAND, M. (1989) · Written Communication · doi:10.1177/0741088389006001005 · Cited by 225 · cited 1×
“Other work on writing has emphasized social-interactive [69] and sociocultural models of writing, studied with a range of social scientiic empirical methods that consider how writing activity is "situated in concrete actions that are simultaneously improvised locally andmediated by prefabricated, historically provided…”
BackgroundGeDi: Generative Discriminator Guided Sequence Generation
Krause, B., Gotmare, A. D., McCann, B., Keskar, N. S., Joty, S., Socher, R., & Rajani, N. F. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.424 · Cited by 220
Event Representations for Automated Story Generation with Deep Neural Nets
Martin, L. J., Ammanabrolu, P., Wang, X., Hancock, W. S., Singh, S., Harrison, B. E., & Riedl, M. O. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11430 · Cited by 201 · cited 1×
“These are often demonstrated by application to automated or semi-automated narrative generation tasks [1, 62, 76], an essentially creative domain.”
BackgroundInfants' Learning about Words and Sounds in Relation to Objects
Woodward, A., & Hoyne, K. (1999) · Child Development · doi:10.1111/1467-8624.00006 · Cited by 181 · cited 1×
“where humans are able to aurally discern the source) have also been shown to impact memory [82], language learning [99], and, as a feedback modality, attention and information communication [42].”
BackgroundThe Language Experience and Proficiency Questionnaire (LEAP-Q): Ten years later
Kaushanskaya, M., Blumenfeld, H. K., & Marian, V. (2020) · Bilingualism: Language and Cognition · doi:10.1017/s1366728919000038 · Cited by 163
Efficient Creativity: Constraint‐Guided Conceptual Combination
Costello, F., & Keane, M. T. (2000) · Cognitive Science · doi:10.1207/s15516709cog2402_4 · Cited by 156
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
Bardzell, J., & Bardzell, S. (2016) · Interactions · doi:10.1145/2888576 · Cited by 144
AI as Social Glue: Uncovering the Roles of Deep Generative AI during Social Music Composition
Suh, M. (., Youngblom, E., Terry, M., & Cai, C. J. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445219 · Cited by 138 · cited 1×
“This type of psychological support function has been recently identiied in other human-AI creative interaction domains [91].”
BackgroundEffects of Language Modeling and its Personalization on Touchscreen Typing Performance
Fowler, A., Partridge, K., Chelba, C., Bi, X., Ouyang, T., & Zhai, S. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702503 · Cited by 127
The Writer's Workbench: Computer Aids for Text Analysis
Macdonald, N. H., Frase, L. T., Gingrich, P. S., & Keenan, S. A. (1982) · IEEE Transactions on Communications · doi:10.1109/tcom.1982.1095380 · Cited by 126 · cited 1×
“Early work on spelling, punctuation, and grammar checking as well as additional textual analysis found that computer assistance could improve writing without substantially increasing writing time, but also found that it prompted users to think critically about their writing when they might not have prior to interactio…”
BackgroundMental Models of AI Agents in a Cooperative Game Setting
Gero, K. I., Ashktorab, Z., Dugan, C., Pan, Q., Johnson, J., Geyer, W., Ruiz, M., Miller, S., Millen, D. R., Campbell, M., et al. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376316 · Cited by 121 · cited 1×
“study human-AI collaboration in a game setting, and their results suggest that understanding of the system alone insuiciently develops appropriate conceptual models [45].”
BackgroundAgent, Person, Subject, Self: A Theory of Ontology, Interaction, and Infrastructure
Kockelman, P. (2012) · Cited by 115
Turner, M. B., & Fauconnier, G. (1999) · Project Muse (Johns Hopkins University) · Cited by 109
Buschek, D., Zürn, M., & Eiband, M. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445372 · Cited by 108 · cited 1×
“, conducted in parallel with ours, has examined the efects of parallel phrase suggestions on writers in an email-writing task [17].”
BackgroundA Cost-Benefit Study of Text Entry Suggestion Interaction
Quinn, P., & Zhai, S. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858305 · Cited by 98
The Psychology of Creative Writing
(2009) · doi:10.1017/cbo9780511627101 · Cited by 93 · cited 1×
“More recent psychological approaches to studying creative writing have emphasized the role of retrieval, conceptual combination, and analogical mapping as some of the fundamental cognitive processes that explain creative cognition [35, 48, 95].”
BackgroundPredictive text encourages predictable writing
Arnold, K. C., Chauncey, K., & Gajos, K. Z. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377523 · Cited by 87 · cited 1×
“examines the efects of predictive text on writing content, inding that eiciency enhancements apply not just to the process of writing but to the range of content emerging from this process as well [3].”
BackgroundWhat's the Folk Theory? Reasoning About Cyber-Social SystemsPreprint
French, M., & Hancock, J. T. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.2910571 · Cited by 85 · cited 1×
“Mental models are structured accounts of a system’s mechanics and behavior, but folk theories and implicit beliefs arise from a great many sources of information and interaction, and are not constrained to nor will they necessarily contain an understanding of "the relationship between inputs and outputs" [40].”
BackgroundCreative 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×
“and Gordon’s Creative Help system makes suggestions that users can edit to incorporate them into stories [85].”
BackgroundG-Asks: An Intelligent Automatic Question Generation System for Academic Writing Support
Liu, M., Calvo, R. A., & Rus, V. (2012) · Dialogue & Discourse · doi:10.5087/dad.2012.205 · Cited by 77 · cited 1×
“For academic writing support, Liu and colleagues [59] introduced G-Asks, a system for improving students’ writing skills, e.”
BackgroundOsone, 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×
“found that more writers enjoyed working with a Japanese generative model than not [70].”
BackgroundOn Suggesting Phrases vs. Predicting Words for Mobile Text Composition
Arnold, K. C., Gajos, K. Z., & Kalai, A. T. (2016) · Proceedings of the 29th Annual Symposium on User Interface Software and Technology · doi:10.1145/2984511.2984584 · Cited by 69 · cited 2×
“provide methods to generate phrase-level continuations and demonstrate their impact by showing that phrase completions can be ofered in a way that they are accepted by the user and interpreted as suggestions rather than predictions [2, 4].”
BackgroundMethodBoth complete and correct? multi-objective optimization of touchscreen keyboard
Bi, X., Ouyang, T. Y., & Zhai, S. (2014) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2556288.2557414 · Cited by 61
Evaluating Computational Creativity: An Interdisciplinary Tutorial
Lamb, C., Brown, D. G., & Clarke, C. L. A. (2019) · ACM Computing Surveys · doi:10.1145/3167476 · Cited by 58
Automated Assistance for Creative Writing with an RNN Language Model
Roemmele, M., & Gordon, A. S. (2018) · Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces · doi:10.1145/3180308.3180329 · Cited by 55 · cited 1×
“In later work, they additionally study how randomness or unpredictability in suggestion can inluence writers’ attitudes, inding that increased randomness lowers ratings of factors like coherence and increases ones like perceived originality [86].”
BackgroundMediated Atmospheres: A Multimodal Mediated Work Environment
Zhao, N., Azaria, A., & Paradiso, J. A. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3090096 · Cited by 50
Dancygier, B. (2006) · Language and Literature International Journal of Stylistics · doi:10.1177/0963947006060549 · Cited by 48
On the Road to Computer Assisted Compositions
Woodruff, E., Bereiter, C., & Scardamalia, M. (1981) · Journal of Educational Technology Systems · doi:10.2190/ehrv-rlv5-evw6-nh58 · Cited by 47 · cited 1×
“[98] found that their high-level composition assistance tool was absorbed into a less critical sequence-of-suggestions text composition strategy, despite reports that it was helpful.”
BackgroundLandry, B. M., & Guzdial, M. (2006) · Designing Interactive Systems Conference · doi:10.1145/1142405.1142432 · Cited by 47
The Algorithm and the User: How Can HCI Use Lay Understandings of Algorithmic Systems?
DeVito, M. A., Hancock, J. T., French, M., Birnholtz, J. P., Antin, J., Karahalios, K. G., Tong, S. T., & Shklovski, I. (2018) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3170427.3186320 · Cited by 46
“I Can’t Reply with That”: Characterizing Problematic Email Reply Suggestions
Robertson, R. E., Olteanu, A., Diaz, F., Shokouhi, M., & Bailey, P. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445557 · Cited by 43
Guided Neural Language Generation for Automated Storytelling
Ammanabrolu, P., Tien, E., Cheung, W., Luo, Z., Ma, W., Martin, L. J., & Riedl, M. O. (2019) · Workshop on Storytelling (StoryNLP) · doi:10.18653/v1/w19-3405 · Cited by 37 · cited 1×
“These are often demonstrated by application to automated or semi-automated narrative generation tasks [1, 62, 76], an essentially creative domain.”
BackgroundWordcraft: a Human-AI Collaborative Editor for Story Writing
Coenen, A., Davis, L., Ippolito, D., Reif, E., & Yuan, A. (2021) · arXiv · doi:10.48550/arxiv.2107.07430 · Cited by 35 · cited 1×
“WordCraft [23] frames the collaboration between a human storyteller and AI within an open-ended dialog system with more explicit turns and turn types than what is implemented in this paper, but the efects of these design choices were not evaluated in a systematic way.”
BackgroundKockelman, P. (2006) · Semiotica · doi:10.1515/sem.2006.072 · Cited by 32
Alphabetic Data Entry via the Touch-Tone Pad: A Comment
Smith, S. L., & Goodwin, N. C. (1971) · Human Factors The Journal of the Human Factors and Ergonomics Society · doi:10.1177/001872087101300212 · Cited by 23 · cited 2×
“For example, Smith and Goodwin [90] investigated lexicon-based single-key vs. double-key typing support for numeric keyboards in context-constrained settings, i.e., for jobs that required such text entry, indicating how computers may help resolve ambiguities arising from the former.”
BackgroundA ‘Cognitive Turn’ in Creative Writing – Cognition, Body and Imagination
Freiman, M. (2015) · New Writing · doi:10.1080/14790726.2015.1016043 · Cited by 22
The Design Space of Nonvisual Word Completion
Nicolau, H., Rodrigues, A., Santos, A., Guerreiro, T., Montague, K., & Guerreiro, J. (2019) · Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3308561.3353786 · Cited by 21 · cited 1×
“identify cardinality as an important design factor for non-visual word completion systems [66].”
BackgroundGabriel, R. P., Chen, J., & Nichols, J. W. (2015) · Creativity and Cognition · doi:10.1145/2757226.2757229 · Cited by 18
Plug-and-Blend: A Framework for Plug-and-Play Controllable Story Generation with Sketches
Lin, Z., & Riedl, M. O. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v17i1.18891 · Cited by 16 · cited 1×
“Such steering can be explicitly enabled [50, 53, 58], for example, by conditional modeling, or, in the absence of specialized approaches, even discovered by so-called "prompt engineering" which has been successfully used(7) by many for language-controlled visual art generation [73] with general-purpose vision+language…”
BackgroundMothersill, P., & Bove, V. M. (2019) · doi:10.1145/3301019.3323909 · Cited by 1
Research works printed but not linked: 21
- Kenneth Arnold Kai-Wei Chang and Adam Kalai. 2017. Counterfactual Language Model Adaptation for Suggesting Phrases. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers) . 49–54.
- Eden Bensaid. 2021. Multimodal generative models for storytelling. Master’s Thesis. Massachusetts Institute of Technology.
- Eden Bensaid Mauro Martino Benjamin Hoover Jacob Andreas and Hendrik Strobelt. 2021. FairyTailor: A multimodal generative framework for storytelling. arXiv:2108.04324. Retrieved from https://arxiv.org/abs/2108.04324. · arXiv
- Lukas Bieringer Kathrin Grosse Michael Backes and Katharina Krombholz. 2021. Mental Models of Adversarial Machine Learning. In ICCV 2021 Workshop on Adversarial Robustness in the Real World .
- Margaret A. Boden. 2004. The creative mind: Myths and mechanisms. Routledge.
- Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger T. J. Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeff Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (2020) 1877–1901.
- Alex Calderwood, Vivian Qiu, Katy Ilonka Gero, and Lydia B. Chilton. 2020. How novelists use generative language models: An exploratory user study. In Proceedings of the HAI-GEN+ user2agent@ IUI.
- Orson Scott Card. 1990. How to Write Science Fiction and Fantasy. Writer’s digest books Cincinnati, OH.
- Michelene T. H. Chi. 2000. Self-explaining expository texts: The dual processes of generating inferences and repairing mental models. Advances in Instructional Psychology 5 (2000), 161–238.
- Stephen R. Donaldson. 2008. The Gap Into Conflict: The Real Story. CNIB.
- Angela Fan Mike Lewis and Yann Dauphin. 2018. Hierarchical Neural Story Generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) . 889–898.
- 10.2307/356600 · doi:10.2307/356600 · Paper page
- 10.1207/s15516709cog1404_3 · doi:10.1207/s15516709cog1404_3 · Paper page
- Roger Levy and Galen Andrew. 2006. Tregex and Tsurgeon: Tools for querying and manipulating tree data structures.. In Proceedings of the LREC. Citeseer, 2231–2234.
- Ellen W. Nold. 1981. Revising. Writing: The Nature, Development, and Teaching of Written Communication 2 (1981), 67–79.
- Ben Pietrzak Ben Swanson Kory Mathewson Monica Dinculescu and Sherol Chen. 2021. Story centaur: Large language model few shot learning as a creative writing tool. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations.
- Paul A. Prior. 2005. A Sociocultural Theory of Writing. In The Handbook of Writing Research . Guilford Press 54–66.
- Alec Radford Jong Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning . PMLR 8748–8763.
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.
- David Ramsay, Ishwarya Ananthabhotla, and Joseph Paradiso. 2019. The intrinsic memorability of everyday sounds. In Proceedings of the Audio Engineering Society Conference: 2019 AES International Conference on Immersive and Interactive Audio. Audio Engineering Society.
- Thomas B. Ward and E. Thomas Lawson. 2009. Creative Cognition in Science Fiction and Fantasy Writing . Cambridge University Press.
Cited by
Brynjolfsson, E., Li, D., & Raymond, L. (2023) · National Bureau of Economic Research · doi:10.3386/w31161 · Cited by 995
“writing suggestion tool, Singh et al. (2022) finds that four of the 23 study participants refused to engage with AI suggestions.”
Co-Writing with Opinionated Language Models Affects Users’ Views
Jakesch, M., Bhat, A., Buschek, D., Zalmanson, L., & Naaman, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581196 · Cited by 265
“Studies have investigated interface design factors and interactions with writing assistants that directly or indirectly support inspiration [17, 70, 95, 105], language prof-ciency [27], story writing [95, 105], text revision [36, 107] or creative writing [33, 46].”
BackgroundDraxler, 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
“Related, Singh et al. [96] describes how writers actively invest into taking ‘leaps’ to fit their story around a suggested phrase.”
BackgroundHomogenization Effects of Large Language Models on Human Creative Ideation
Anderson, B. R., Shah, J. H., & Kreminski, M. (2024) · Creativity and Cognition · doi:10.1145/3635636.3656204 · Cited by 188
3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows
Liu, V., Vermeulen, J., Fitzmaurice, G., & Matejka, J. (2023) · Proceedings of the 2023 ACM Designing Interactive Systems Conference · doi:10.1145/3563657.3596098 · Cited by 163
“3DALL-E’s interdisciplinary design knowledge is both a strength of AI pretraining as well as the ability of designers to make integrative leaps to meet the AI halfway [81].”
Background
Metadata
- Authors
- Singh, N., Bernal, G., Savchenko, D., & Glassman, E. L.
- Affiliations
- MIT Media Lab (US)
- Harvard University (US)
- Venue
- ACM Transactions on Computer-Human Interaction
- Published
- 2023-09-23
- Volume
- 30
- Issue
- 5
- Pages
- 1-57
- ISSN
- 1073-0516 (ISSN-L)
- 1557-7325
- OpenAlex
- W4213451626
- Cited by
- 119
- References
- 77
- Citations by year
- 2026: 15 · 2025: 32 · 2024: 38 · 2023: 23
- FWCI
- 12.82
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Transactions on Computer-Human Interaction (publishedVersion, cc-by)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- Funders
- NSF (2107391)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Artistic and Creative Research
- Keywords
- creative writing, language models, text generation, human-AI collaboration, story development
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
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.