The DOI matches its Crossref record; 28 of the 29 references it cites were found in a registry or an index; 7 of the 15 sources its claims cite were checked for support.
Generating Together: Lessons Learned from Developing an Educational Visual Novel with AI Collaboration
Open accessAbstract
Visual novels are a popular game genre for educational games. However, they often feature pre-authored plot structures that cannot dynamically adjust to the player’s progression through learning objectives. Employing procedural storytelling techniques boosts plot dynamism, but this comes at the cost of needing a larger repository of content (dialogue and images) to support different learning progressions and objectives. In this paper, we present postmortem-style case studies describing the lessons we learned from attempting to integrate large-language models (LLMs) and text-to-image models into the development of an educational visual novel about responsible conduct of research. Specifically, we discuss our experiences employing generative AI in our dialogue, character sprite, and background image creation processes.
Overview
CoChat Summary
TL;DR
This paper presents postmortem-style case studies from integrating large language models and text-to-image models into the development of an educational visual novel about responsible conduct of research. It finds generative AI useful for augmentation and brainstorming but not as a full replacement for writers and artists, requiring heavy human oversight and proving unsuitable for background image generation.
Key findings
- ChatGPT could generate utterances meeting high-level goals, but final content needed heavy revision: text was verbose and literal, dialogue was stiff, and very little LLM-generated text made it through multiple rewrites.
- Stable Diffusion 1.5 fine-tuned on a roughly 20-image corpus, with training sets of 15–20 images, produced usable character portraits but required postprocessing, many generation attempts due to non-determinism, and did not accelerate the overall pace of development.
- Stable Diffusion was judged not appropriate for location backgrounds because objects were excluded or moved, spatial layout changed between images, perspective was often incorrect, and object scale varied unrealistically.
- The production team comprised 3 writers, 1 2D/3D artist, 1 generative artist, 3 system engineers, and 1 producer; the paper frames generative techniques as creative augmentation rather than artist displacement.
Methods
- Design: postmortem-style case studies of integrating generative AI into game production, following the postmortem approach of highlighting goals, technology, what went right, what went wrong, and what should have been done instead.
- Data/sample: the development process of Academical 2.0, an educational visual novel about responsible conduct of research, with three case studies covering narrative generation with ChatGPT, character portrait generation with Stable Diffusion 1.5, and location background generation with Stable Diffusion.
- Analysis: qualitative lessons learned from an interdisciplinary team of writers, artists, and programmers, including writer’s room practices, concept formation, model fine-tuning, and artist interview responses.
Limitations
- Stated: future versions of Academical will lessen the use of generative AI in production due to the limitations encountered; the project occurred in an academic environment with low resources and contributors focused on training specific roles.
- Evident: no comparison study between Academical 1.0 and 2.0 had yet been conducted, as it is listed as future work, so learning-outcome and ARC-factor effects are not evaluated here.
- Evident: the findings come from a single project’s qualitative postmortem and artist interview, with no quantitative benchmark or generalizable production study reported.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
7 Valid · 1 Not valid · 8 Not checked · 37 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“A case study of game proposals demonstrated that generative AI was a major boon to creating concept and prototyping assets, bolstering our findings that these systems are ideal for prompting imagination and game vision. [34]”
What the sources say
- Supportedcites [34] source
The Introduction (p. 2) describes a comparison of game design documents made with and without generative AI. The AI and Games section (p. 3) identifies concept art and prototype art resources as part of creating proposals, while the Project NOX case (p. 7) reports rapid generation of artwork that stimulated designers’ ideas. (LLM, conf=0.90)
boostedstates a 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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“A case study of game proposals demonstrated that generative AI was a major boon to creating concept and prototyping assets, bolstering our findings that these systems are ideal for prompting imagination and game vision. [34]”
What the sources say
- Supportedcites [34] source
The Project NOX case study (p. 7) says generative AI helped create concept artwork, sparked additional ideas, and stimulated designers’ imagination. The proposal discussion (p. 13) reports faster creation of intended characters and buildings and greater creative freedom, supporting the cited sentence’s point about developing game concepts and visual assets. (LLM, conf=0.90)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — 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
“A core theme of this project is that generative techniques are not strong replacements for core creative activities but are better at augmenting creative output to solve key tensions in traditional game development - such as authoring similar portraits for a single character.”
What the sources say
- Supportedcites [8] source
The Concluding remarks (p. 51) say that significant challenges remain for AI as the sole generator of original work and conclude that creative applications should augment, rather than replace, human creativity. This supports the attributed point about generative techniques; the game-development example is the citing authors’ application of that point. (LLM, conf=0.94)
boosted- 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.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the final content needed high amounts of revision to be included in the production game.”
plainSingle case- 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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While Stable Diffusion 1.5 provided a consistent representation of characters with additional training, initial testing of fine-tuning locations produced images with high levels of inconsistency.”
plainstates 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.
22 more claims
Create a free account to see all 53 claims and every source verdict.
- Probably not a substantial claim. 14
- It may state two separate claims as one. 18
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 cited source says what the claim attributes to it.
In the citing paper
“Shifting toward a production-oriented model, Shields et al. [67] documented a US serious games project where students and academics develop an educational visual novel.”
From Generative AI in Game Development: A Qualitative Research Synthesis (2026) · cites this paper as [67]
The cited source says what the claim attributes to it.
In the citing paper
“Like Boucher et al., the work simulated professional production but within academic constraints, with managing GenAI assets proving as time-consuming as traditional art.”
From Generative AI in Game Development: A Qualitative Research Synthesis (2026) · cites this paper as [67]
Citations
Cites
The motivational pull of video games: a self-determination theory approach
Ryan, R. M., Rigby, C. S., & Przybylski, A. (2006) · Motivation and Emotion · doi:10.1007/s11031-006-9051-8 · Cited by 3,332 · cited 1×
“Recent work on Academical has examined it through the lens of Self-Determination Theory [23] to better understand how certain elements of Academical’s design influence different Self-Determination Theory factors and, subsequently, player experience, as well as how such elements could be changed to…”
BackgroundArtificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793 · cited 2×
“Conversely, there is a complementary fear that these tools may not prove useful as people attempt to employ them to produce actual games rather than speculative tools and demos [8].”
BackgroundMixed-initiative co-creativity
Yannakakis, G. N., Liapis, A., & Alexopoulos, C. (2014) · OAR@UM (University of Malta) · Cited by 299
AI Art and its Impact on Artists
Jiang, H. H., Brown, L., Cheng, J., Khan, M., Gupta, A., Workman, D., Hanna, A., Flowers, J., & Gebru, T. (2023) · Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3600211.3604681 · Cited by 265 · cited 1×
“Generative artificial intelligence has provided an alluring space for individuals producing games, as it has the potential to produce assets with high enough fidelity to use in published games at a much faster clip than traditional approaches [5].”
BackgroundLevel Generation Through Large Language Models
Todd, G., Earle, S., Nasir, M. U., Green, M. C., & Togelius, J. (2023) · International Conference on the Foundations of Digital Games (FDG) · doi:10.1145/3582437.3587211 · Cited by 182 · cited 1×
“There has been a significant quantity of recent work using large language models to address various game design tasks – for instance, generating interactive stories [16], 2D Game Levels [17], and quest generation [18].”
BackgroundGenerating Role-Playing Game Quests With GPT Language Models
Värtinen, S., Hämäläinen, P., & Guckelsberger, C. (2022) · IEEE Transactions on Games · doi:10.1109/tg.2022.3228480 · Cited by 121 · cited 1×
“There has been a significant quantity of recent work using large language models to address various game design tasks – for instance, generating interactive stories [16], 2D Game Levels [17], and quest generation [18].”
BackgroundVimpari, V., Kultima, A., Hämäläinen, P., & Guckelsberger, C. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3611025 · Cited by 77 · cited 2×
“This advantage, however, has increased the fear that these tools will be used to replace traditional game development roles such as writers and artists [6].”
BackgroundDevelopment of Role-Play Scenarios for Teaching Responsible Conduct of Research
Brummel, B. J., Gunsalus, C. K., Anderson, K. L., & Loui, M. C. (2010) · Science and Engineering Ethics · doi:10.1007/s11948-010-9221-7 · Cited by 76
Mixed-initiative content creation
Liapis, A., Smith, G., & Shaker, N. (2016) · Computational Synthesis and Creative Systems · doi:10.1007/978-3-319-42716-4_11 · Cited by 71 · cited 1×
“Research on mixed-initiative co-creative AI systems focuses on developing workflows that allow humans and computational generative systems to work collaboratively to create things that neither could easily create independently [9], [12].”
BackgroundLanguage as Reality: A Co-Creative Storytelling Game Experience in 1001 Nights Using Generative AI
Sun, Y., Li, Z., Fang, K., Lee, C. H., & Asadipour, A. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27539 · Cited by 63
Research works printed but not linked: 9
- Martens, Procedural narrative generation
- Yannakakis, Mixed-initiative cocreativity
- Whitten, 2023, Introducing unity muse and unity sentis, ai-powered creativity, Unity Blog
- Burnes, 2023, Introducing nvidia ace for games-spark life into virtual characters with generative ai, NVIDIA GeForce
- Fowler, 2001, The agile manifesto, Software development, 9, 28
- Junius, 2019, Puppitor: Building an Acting Interface for Videogames. University of California
- Samuel, Leveraging procedural narrative and gameplay to address controversial topics
- Hills, 2022, Management fads: How to resist shiny object syndrome, Physician Leadership Journal, 9
- Dini, 2023, 7-cocreation of serious games to acquire a professional skill, EXECUTIVE COMMITTEE
Cited by
Designing a Narrative-Centered Game to Promote AI Literacy and Health Career Exploration
Mott, B., Vandenberg, J. L., Penilla, C., Hennigan, S., Navarro, R., Lester, J. C., & Ozer, E. M. (2025) · IEEE Conference on Games (CoG) · doi:10.1109/cog64752.2025.11114233 · Cited by 3
“Recent work has also explored the potential of generative AI to support the collaborative creation of educational narratives, such as visual novels [9].”
Generative AI in Game Development: A Qualitative Research Synthesis
Ternar, D.-A., Denisova, A., Cunha, J. M., Kultima, A., & Guckelsberger, C. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791206 · Cited by 6
“Shifting toward a production-oriented model, Shields et al. [67] documented a US serious games project where students and academics develop an educational visual novel.”
Kim, T., & Kim, T. (2026) · Journal of Digital Contents Society · doi:10.9728/dcs.2026.27.5.1401 · Cited by 1
Adaptive AI NPCS with Evolving Storylines for an Educational Game
S, A. P., Reddy, S., V, Yeshas, R., et al. (2026) · doi:10.1109/ccic68129.2026.11486263
“It has been demonstrated that as a result of this, knowledge retention decreases and the initial student curiosity fades away [3], [4].”
Leidel, J., Reichert, T., & Marsden, N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30405-6_6
Metadata
- Authors
- Shields, S., Calderwood, A., Johnson-Bey, S., Wardrip-Fruin, N., Mateas, M., & Melcer, E.
- Affiliations
- University of California, Santa Cruz (US)
- University of California, Santa Cruz,Computational Media,Santa Cruz,United States
- Venue
- 2024 IEEE Conference on Games (CoG)
- Publisher
- IEEE
- Published
- 2024-08-05
- Pages
- 1-8
- OpenAlex
- W4401943823
- Semantic Scholar
- 246c740288c21c67d7dd6e92f77b55af2257450c
- Cited by
- 11
- References
- 29
- Citations by year
- 2026: 10 · 2025: 1
- FWCI
- 1.74
- Type
- conference paper
- Language
- en
- Open access
- green
- escholarship.org
- Locations
- IEEE Conference on Games (CoG) (publishedVersion)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Social Sciences › Psychology › Developmental and Educational Psychology › Educational Games and Gamification
- Social Sciences › Education › Artificial Intelligence in Education
- Keywords
- generative AI, large language models, text-to-image models, responsible conduct of research, game development, dialogue generation, collaborative game 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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Generating Together: Lessons Learned from Developing an Educational Visual Novel with AI Collaboration. https://app.cochat.ai/papers/10.1109/cog60054.2024.10645553
- The paper
- Shields, S., Calderwood, A., Johnson-Bey, S., Wardrip-Fruin, N., Mateas, M., & Melcer, E. (2024). Generating Together: Lessons Learned from Developing an Educational Visual Novel with AI Collaboration. 2024 IEEE Conference on Games (CoG). https://doi.org/10.1109/cog60054.2024.10645553
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.