@inproceedings{10.1145/3491102.3517582,
author = {Wu, Tongshuang and Terry, Michael and Cai, Carrie Jun},
title = {AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts},
year = {2022},
isbn = {9781450391573},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3491102.3517582},
doi = {10.1145/3491102.3517582},
abstract = {Although large language models (LLMs) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, we introduce the concept of Chaining LLM steps together, where the output of one step becomes the input for the next, thus aggregating the gains per step. We first define a set of LLM primitive operations useful for Chain construction, then present an interactive system where users can modify these Chains, along with their intermediate results, in a modular way. In a 20-person user study, we found that Chaining not only improved the quality of task outcomes, but also significantly enhanced system transparency, controllability, and sense of collaboration. Additionally, we saw that users developed new ways of interacting with LLMs through Chains: they leveraged sub-tasks to calibrate model expectations, compared and contrasted alternative strategies by observing parallel downstream effects, and debugged unexpected model outputs by “unit-testing” sub-components of a Chain. In two case studies, we further explore how LLM Chains may be used in future applications.},
booktitle = {Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems},
articleno = {385},
numpages = {22},
keywords = {Large Language Models, Natural Language Processing, Human-AI Interaction},
location = {New Orleans, LA, USA},
series = {CHI '22},
month = {04}
}


@inproceedings{10.1145/3490099.3511105,
author = {Yuan, Ann and Coenen, Andy and Reif, Emily and Ippolito, Daphne},
title = {Wordcraft: Story Writing With Large Language Models},
year = {2022},
isbn = {9781450391443},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3490099.3511105},
doi = {10.1145/3490099.3511105},
abstract = {The latest generation of large neural language models such as GPT-3 have achieved new levels of performance on benchmarks for language understanding and generation. These models have even demonstrated an ability to perform arbitrary tasks without explicit training. In this work, we sought to learn how people might use such models in the process of creative writing. We built Wordcraft, a text editor in which users collaborate with a generative language model to write a story. We evaluated Wordcraft with a user study in which participants wrote short stories with and without the tool. Our results show that large language models enable novel co-writing experiences. For example, the language model is able to engage in open-ended conversation about the story, respond to writers’ custom requests expressed in natural language (such as ”rewrite this text to be more Dickensian”), and generate suggestions that serve to unblock writers in the creative process. Based on these results, we discuss design implications for future human-AI co-writing systems.},
booktitle = {27th International Conference on Intelligent User Interfaces},
pages = {841–852},
numpages = {12},
keywords = {NLP},
location = {Helsinki, Finland},
series = {IUI '22},
month = {03}
}


@misc{dibia2023lida,
title = {LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models},
author = {Victor Dibia},
year = {2023},
eprint = {2303.02927},
archivePrefix = {arXiv},
primaryClass = {cs.AI},
month = {03}
}


@misc{jiang2023graphologue,
title = {Graphologue: Exploring Large Language Model Responses with Interactive Diagrams},
author = {Peiling Jiang and Jude Rayan and Steven P. Dow and Haijun Xia},
year = {2023},
eprint = {2305.11473},
archivePrefix = {arXiv},
primaryClass = {cs.HC},
month = {05}
}


@inproceedings{10.1145/3544548.3581560,
author = {Valencia, Stephanie and Cave, Richard and Kallarackal, Krystal and Seaver, Katie and Terry, Michael and Kane, Shaun K.},
title = {“The Less I Type, the Better”: How AI Language Models Can Enhance or Impede Communication for AAC Users},
year = {2023},
isbn = {9781450394215},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3544548.3581560},
doi = {10.1145/3544548.3581560},
abstract = {Users of augmentative and alternative communication (AAC) devices sometimes find it difficult to communicate in real time with others due to the time it takes to compose messages. AI technologies such as large language models (LLMs) provide an opportunity to support AAC users by improving the quality and variety of text suggestions. However, these technologies may fundamentally change how users interact with AAC devices as users transition from typing their own phrases to prompting and selecting AI-generated phrases. We conducted a study in which 12 AAC users tested live suggestions from a language model across three usage scenarios: extending short replies, answering biographical questions, and requesting assistance. Our study participants believed that AI-generated phrases could save time, physical and cognitive effort when communicating, but felt it was important that these phrases reflect their own communication style and preferences. This work identifies opportunities and challenges for future AI-enhanced AAC devices.},
booktitle = {Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems},
articleno = {830},
numpages = {14},
keywords = {communication, artificial intelligence, large language models, accessibility},
location = {Hamburg, Germany},
series = {CHI '23},
month = {04}
}


@misc{koh2023generating,
title = {Generating Images with Multimodal Language Models},
author = {Jing Yu Koh and Daniel Fried and Ruslan Salakhutdinov},
year = {2023},
eprint = {2305.17216},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
month = {05}
}


@misc{cai2023lowcode,
title = {Low-code LLM: Visual Programming over LLMs},
author = {Yuzhe Cai and Shaoguang Mao and Wenshan Wu and Zehua Wang and Yaobo Liang and Tao Ge and Chenfei Wu and Wang You and Ting Song and Yan Xia and Jonathan Tien and Nan Duan},
year = {2023},
eprint = {2304.08103},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
month = {04}
}


@inproceedings{swanson-etal-2021-story,
title = {Story Centaur: Large Language Model Few Shot Learning as a Creative Writing Tool},
author = {Swanson, Ben and
Mathewson, Kory and
Pietrzak, Ben and
Chen, Sherol and
Dinalescu, Monica},
booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations},
month = {04},
year = {2021},
address = {Online},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2021.eacl-demos.29},
doi = {10.18653/v1/2021.eacl-demos.29},
pages = {244--256},
abstract = {Few shot learning with large language models has the potential to give individuals without formal machine learning training the access to a wide range of text to text models. We consider how this applies to creative writers and present Story Centaur, a user interface for prototyping few shot models and a set of recombinable web components that deploy them. Story Centaur{'}s goal is to expose creative writers to few shot learning with a simple but powerful interface that lets them compose their own co-creation tools that further their own unique artistic directions. We build out several examples of such tools, and in the process probe the boundaries and issues surrounding generation with large language models.}
}


@misc{mishra2023promptaid,
title = {PromptAid: Prompt Exploration, Perturbation, Testing and Iteration using Visual Analytics for Large Language Models},
author = {Aditi Mishra and Utkarsh Soni and Anjana Arunkumar and Jinbin Huang and Bum Chul Kwon and Chris Bryan},
year = {2023},
eprint = {2304.01964},
archivePrefix = {arXiv},
primaryClass = {cs.HC},
month = {04}
}


@article{akoury2020storium,
title = {Hierarchical neural story generation},
author = {Fan, Angela and Lewis, Mike and Dauphin, Yann},
journal = {arXiv preprint arXiv:1805.04833},
year = {2018},
month = {12}
}


@article{akoury2020storium,
title = {Attention is all you need},
author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
journal = {Advances in neural information processing systems},
volume = {30},
year = {2017},
month = {12}
}


@inproceedings{10.1145/3544548.3581196,
author = {Jakesch, Maurice and Bhat, Advait and Buschek, Daniel and Zalmanson, Lior and Naaman, Mor},
title = {Co-Writing with Opinionated Language Models Affects Users’ Views},
year = {2023},
isbn = {9781450394215},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3544548.3581196},
doi = {10.1145/3544548.3581196},
abstract = {If large language models like GPT-3 preferably produce a particular point of view, they may influence people’s opinions on an unknown scale. This study investigates whether a language-model-powered writing assistant that generates some opinions more often than others impacts what users write – and what they think. In an online experiment, we asked participants (N=1,506) to write a post discussing whether social media is good for society. Treatment group participants used a language-model-powered writing assistant configured to argue that social media is good or bad for society. Participants then completed a social media attitude survey, and independent judges (N=500) evaluated the opinions expressed in their writing. Using the opinionated language model affected the opinions expressed in participants’ writing and shifted their opinions in the subsequent attitude survey. We discuss the wider implications of our results and argue that the opinions built into AI language technologies need to be monitored and engineered more carefully.},
booktitle = {Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems},
articleno = {111},
numpages = {15},
keywords = {GPT-3, risks of large language models, Co-writing, opinion change},
location = {Hamburg, Germany},
series = {CHI '23},
month = {04}
}


@InProceedings{10.1145/3544548.3580969,
author = {Bala, Paulo
and James, Stuart
and Del Bue, Alessio
and Nisi, Valentina},
editor = {Vosmeer, Mirjam
and Holloway-Attaway, Lissa},
title = {Writing with (Digital) Scissors: Designing a Text Editing Tool for Assisted Storytelling Using Crowd-Generated Content},
booktitle = {Interactive Storytelling},
year = {2022},
publisher = {Springer International Publishing},
address = {Cham},
pages = {139--158},
abstract = {Digital Storytelling can exploit numerous technologies and sources of information to support the creation, refinement and enhancement of a narrative. Research on text editing tools has created novel interactions that support authors in different stages of the creative process, such as the inclusion of crowd-generated content for writing. While these interactions have the potential to change workflows, integration of these in a way that is useful and matches users' needs is unclear. In order to investigate the space of Assisted Storytelling, we designed and conducted a study to analyze how users write and edit a story about Cultural Heritage using an auxiliary source like Wikipedia. Through a diffractive analysis of stories, creative processes, and social and cultural contexts, we reflect and derive implications for design. These were applied to develop an AI-supported text editing tool using crowd-sourced content from Wikipedia and Wikidata.},
isbn = {978-3-031-22298-6},
month = {12}
}


@inproceedings{10.1145/3526113.3545672,
author = {Dang, Hai and Benharrak, Karim and Lehmann, Florian and Buschek, Daniel},
title = {Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries},
year = {2022},
isbn = {9781450393201},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3526113.3545672},
doi = {10.1145/3526113.3545672},
abstract = {We propose a text editor to help users plan, structure and reflect on their writing process. It provides continuously updated paragraph-wise summaries as margin annotations, using automatic text summarization. Summary levels range from full text, to selected (central) sentences, down to a collection of keywords. To understand how users interact with this system during writing, we conducted two user studies (N=4 and N=8) in which people wrote analytic essays about a given topic and article. As a key finding, the summaries gave users an external perspective on their writing and helped them to revise the content and scope of their drafted paragraphs. People further used the tool to quickly gain an overview of the text and developed strategies to integrate insights from the automated summaries. More broadly, this work explores and highlights the value of designing AI tools for writers, with Natural Language Processing (NLP) capabilities that go beyond direct text generation and correction.},
booktitle = {Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology},
articleno = {98},
numpages = {13},
keywords = {semantic zoom, text summarization, Natural Language Processing, reverse outlining, Text documents},
location = {Bend, OR, USA},
series = {UIST '22},
month = {10}
}


@inproceedings{yang2022ai,
title = {AI as an Active Writer: Interaction strategies with generated text in human-AI collaborative fiction writing},
author = {Yang, Daijin and Zhou, Yanpeng and Zhang, Zhiyuan and Li, Toby Jia-Jun and LC, Ray},
booktitle = {Joint Proceedings of the ACM IUI Workshops},
volume = {10},
year = {2022},
organization = {CEUR-WS Team},
month = {12}
}


@article{yang2022ai,
author = {Singh, Nikhil and Bernal, Guillermo and Savchenko, Daria and Glassman, Elena L.},
title = {Where to Hide a Stolen Elephant: Leaps in Creative Writing with Multimodal Machine Intelligence},
year = {2022},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
issn = {1073-0516},
url = {https://doi.org/10.1145/3511599},
doi = {10.1145/3511599},
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 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.},
note = {Just Accepted},
journal = {ACM Trans. Comput.-Hum. Interact.},
month = {02},
keywords = {multimodal, audio, interface, images, human-AI interaction, writing, AI, story, audiovisual, creativity support}
}


@inproceedings{10.1609/aiide.v18i1.21955,
author = {Kreminski, Max and Dickinson, Melanie and Wardrip-Fruin, Noah and Mateas, Michael},
title = {Loose Ends: A Mixed-Initiative Creative Interface for Playful Storytelling},
year = {2022},
isbn = {978-1-57735-877-0},
publisher = {AAAI Press},
url = {https://doi.org/10.1609/aiide.v18i1.21955},
doi = {10.1609/aiide.v18i1.21955},
abstract = {We present Loose Ends, a mixed-initiative co-creative storytelling play experience in which a human player and an AI system work together to compose a story. Loose Ends specifically aims to provide computational support for managing multiple parallel plot threads and bringing these threads to satisfying conclusions—something that has proven difficult in past attempts to facilitate playful mixed-initiative storytelling. We describe the overall human-AI interaction loop in Loose Ends, including the implementation of the rules-based AI system that enables this interaction loop; discuss four examples of desirable mixed-initiative interactions that are possible in Loose Ends, but not in similar systems; and present results from a preliminary expert evaluation of Loose Ends. Altogether, we find that Loose Ends shows promise for creating a sense of coauthorship in the player while also mitigating the directionlessness reported by players of earlier systems.},
booktitle = {Proceedings of the Eighteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment},
articleno = {15},
numpages = {9},
location = {Pomona, CA, USA},
series = {AIIDE'22},
month = {12}
}


@misc{10.1609/aiide.v18i1.21955,
title = {Parachute: Evaluating Interactive Human-LM Co-writing Systems},
author = {Hua Shen and Tongshuang Wu},
year = {2023},
eprint = {2303.06333},
archivePrefix = {arXiv},
primaryClass = {cs.HC},
month = {03}
}


@inproceedings{10.1609/aiide.v18i1.21955,
title = {What Can’t Large Language Models Do? The Future of AI-Assisted Academic Writing},
author = {Fok, Raymond and Weld, Daniel S},
booktitle = {In2Writing Workshop at CHI},
year = {2023},
month = {12}
}