Plug-and-Blend: A Framework for Plug-and-Play Controllable Story Generation with Sketches
Open accessAbstract
Large pre-trained neural language models (LM) have very powerful text generation capabilities. However, in practice, they are hard to control for creative purposes. We describe a Plug-and-Play controllable language generation framework, Plug-and-Blend, that allows a human user to input multiple control codes (topics). In the context of automated story generation, this allows a human user loose or fine-grained control of the topics and transitions between them that will appear in the generated story, and can even allow for overlapping, blended topics. Automated evaluations show our framework, working with different generative LMs, controls the generation towards given continuous-weighted control codes while keeping the generated sentences fluent, demonstrating strong blending capability. A human participant evaluation shows that the generated stories are observably transitioning between two topics.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Early research on procedural narrative generation primarily focused on creating coherent sequences of events; however, this alone may fail to produce an engaging narrative that responds dynamically to the player.
“Early research on procedural narrative generation primarily focused on creating coherent sequences of events; however, this alone may fail to produce an engaging narrative that responds dynamically to the player (Lin and Riedl 2021).”
From PANGeA: Procedural Artificial Narrative Using Generative AI for Turn-Based, Role-Playing Video Games (2024) · cites this paper as Lin and Riedl 2021
The Control Model section says earlier procedural story-generation work attempted to produce stories with constrained plots and entities. The Introduction also says prompt-only neural generation is difficult to control in iterative co-creative work. Neither passage establishes that early work primarily focused on coherent event sequences or that such sequences fail to engage players or respond dynamically to them; the paper discusses creator control, not player responsiveness. The indexed passages provide no page numbers. (LLM, conf=0.82)
Experimental — accuracy not yet measuredIngesting free-form text for a video game poses challenges, as it can prompt the LLM to generate content beyond the intended narrative scope.
“Ingesting free-form text for a video game poses challenges, however, as it can prompt the LLM to generate content beyond the intended narrative scope.”
From PANGeA: Procedural Artificial Narrative Using Generative AI for Turn-Based, Role-Playing Video Games (2024) · cites this paper as Lin and Riedl 2021
The Introduction says language models are difficult to control beyond a prompt and that game-story creation requires guidance by context and topic constraints. The Preliminaries likewise describe prompt-based continuations as uncontrolled. These passages support the concern about generation straying from an intended story, but the paper does not specifically discuss ingesting free-form text for a video game. (LLM, conf=0.81)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473 · see citing works
Toward Controlled Generation of TextPreprint
Hu, Z., Yang, Z., Liang, X., Salakhutdinov, R., & Xing, E. P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00955 · Cited by 802 · see citing works
CTRL: 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 · see citing works
Universal Adversarial Triggers for Attacking and Analyzing NLP
Wallace, E., Feng, S., Kandpal, N., Gardner, M., & Singh, S. (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/d19-1221 · Cited by 642 · see citing works
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
Dathathri, S., Madotto, A., Lan, J., Hung, J., Frank, E., Molino, P., Yosinski, J., & Liu, R. (2019) · arXiv · doi:10.48550/arxiv.1912.02164 · Cited by 508 · see citing works
Plan-and-Write: Towards Better Automatic Storytelling
Yao, L., Peng, N., Weischedel, R., Knight, K. K., Zhao, D., & Yan, R. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017378 · Cited by 328 · see citing works
GeDi: 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 · see citing works
A Survey on Story Generation Techniques for Authoring Computational Narratives
Kybartas, B., & Bidarra, R. (2016) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2016.2546063 · Cited by 146 · see citing works
PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
Rashkin, H., Çelikyılmaz, A., Choi, Y., & Gao, J. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.349 · Cited by 130 · see citing works
A Corpus and Evaluation Framework for Deeper Understanding of Commonsense StoriesPreprint
Mostafazadeh, N., Chambers, N., He, X., Parikh, D., Batra, D., Vanderwende, L., Kohli, P., & Allen, J. F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.01696 · Cited by 111 · see citing works
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation
Akoury, N., Wang, S., Whiting, J., Hood, S., Peng, N., & Iyyer, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.525 · Cited by 85 · see citing works
Co-Creative Level Design via Machine Learning
Guzdial, M., Liao, N., & Riedl, M. (2018) · arXiv · doi:10.48550/arxiv.1809.09420 · Cited by 56 · see citing works
Self-citationTransformer-based Conditional Variational Autoencoder for Controllable Story GenerationPreprint
Fang, L., Zeng, T., Liu, C., Bo, L., Dong, W., & Chen, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00828 · Cited by 53 · see citing works
UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation
Guan, J., & Huang, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.736 · Cited by 50 · see citing works
Plug-and-Play Conversational Models
Madotto, A., Ishii, E., Lin, Z., Dathathri, S., & Fung, P. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.219 · Cited by 47 · see citing works
Self-citationPlug and Play Autoencoders for Conditional Text Generation
Mai, F., Pappas, N., Montero, I., Smith, N. A., & Henderson, J. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.491 · Cited by 40 · see citing works
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
Duan, Y., Xu, C., Pei, J., Han, J., & Li, C. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.23 · Cited by 30 · see citing works
Narrative Interpolation for Generating and Understanding StoriesPreprint
Wang, S., Durrett, G., & Erk, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07466 · Cited by 28 · see citing works
Directed Beam Search: Plug-and-Play Lexically Constrained Language GenerationPreprint
Pascual, D., Egressy, B., Bolli, F., & Wattenhofer, R. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.15416 · Cited by 10 · see citing works
On-the-Fly Controlled Text Generation with Experts and Anti-Experts.Preprint
Liu, A., Sap, M., Lu, X., Swayamdipta, S., Bhagavatula, C., Smith, N. A., & Choi, Y. (2021) · arXiv (Cornell University) · Cited by 9 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- Brown, T. B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; Agarwal, S.; Herbert-Voss, A.; Krueger, G.; Henighan, T.; Child, R.; Ramesh, A.; Ziegler, D. M.; Wu, J.; Winter, C.; Hesse, C.; Chen, M.; Sigler, E.; Litwin, M.; Gray, S.; Chess, B.; Clark, J.; Berner, C.; McCandlish, S.; Radford, A.; Sutskever, I.; and Amodei, D. 2020. Language Mod- els are Few-Shot Learners URL https://arxiv.org/abs/2005.
Cited by
Sorted by citations
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models
Zhang, H., Song, H., Li, S., Zhou, M., & Song, D. (2024) · ACM Computing Surveys · doi:10.1145/3617680 · Cited by 317 · see citing works
Where 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 · see citing works
Kumaran, V., Rowe, J., Mott, B., & Lester, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27504 · Cited by 78 · see citing works
PANGeA: Procedural Artificial Narrative Using Generative AI for Turn-Based, Role-Playing Video Games
Buongiorno, S., Klinkert, L., Zhuang, Z., Chawla, T., & Clark, C. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v20i1.31876 · Cited by 37 · see citing works
DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation
Zhang, H., & Song, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.223 · Cited by 27 · see citing works
NarrativeGenie: Generating Narrative Beats and Dynamic Storytelling with Large Language Models
Kumaran, V., Rowe, J., & Lester, J. C. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v20i1.31868 · Cited by 17 · see citing works
Creative Wand: A System to Study Effects of Communications in Co-creative Settings
Lin, Z., Agarwal, R., & Riedl, M. O. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v18i1.21946 · Cited by 9 · see citing works
Self-citationAir-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation
Zhong, T., Wang, Q., Han, J., Zhang, Y., & Mao, Z. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.512 · Cited by 8 · see citing works
LongStory: Coherent, Complete and Length Controlled Long Story Generation
Park, K., Yang, N., & Jung, K. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2253-2_15 · Cited by 7 · see citing works
Text-Only Training for Visual Storytelling
Wang, Y., Zhou, W., Lu, Z., & Li, H. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612179 · Cited by 5 · see citing works
Story Shaping: Teaching Agents Human-Like Behavior with Stories
Peng, X., Cui, C., Zhou, W. G., Jia, R., & Riedl, M. O. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27528 · Cited by 2 · see citing works
Self-citationSemantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation
Zhang, Z., Wu, M., & Zhu, K. Q. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.817 · Cited by 3 · see citing works
Topic-Oriented Controlled Text Generation for Social Networks
Yang, Z., Jiang, H., Deng, A., & Li, Y. (2024) · Journal of Signal Processing Systems · doi:10.1007/s11265-023-01907-2 · Cited by 2 · see citing works
KeYric: Unsupervised Keywords Extraction and Expansion from Music for Coherent Lyrics Generation
Ma, X., Sharma, V., Kan, M., Lee, W. S., & Wang, Y. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3699717 · Cited by 1 · see citing works
Emotional Text Generation with Hard Constraints
Gong, Z., & Li, B. (2022) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic57696.2022.10075091 · Cited by 1 · see citing works
Optimizing Multi-feature Dependent Story Generation Model
Ma, J., Hou, H., Zhao, Y., Sun, S., Chen, W., & Shi, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5669-8_13
Multi Level Vision Language Adapter
Kawamae, N. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00139
- Authors
- Lin, Z., & Riedl, M. O.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Published
- 2021-10-04
- Volume
- 17
- Issue
- 1
- Pages
- 58-65
- ISSN
- 2326-909X (ISSN-L)
- 2334-0924
- OpenAlex
- W3212560870
- Cited by
- 16
- References
- 21
- Citations by year
- 2025: 1 · 2024: 5 · 2023: 6 · 2022: 4
- FWCI
- 1.73
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- controllable text generation, story generation, topic shift, control codes, neural language models, automated story generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
