InkWell

Gabriel, Richard P.; Chen, Jilin; Nichols, Jeffrey

doi:10.1145/2757226.2757229

Cited by 10 publications

(9 citation statements)

References 15 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to their restrictive nature, these technologies were succeeded by generative deep learning models that can produce longer responses that are more open-ended and inventive than their earlier counterparts [67,70]. This shift redefines AI as an active collaborator, expanding its use in diverse contexts like story writing [7,18,40,62,63,74] and creative tasks [19,25,28,41,72]. These adaptable models support specialized tasks such as journalistic ideation [55], visual storyboarding [18], screenplay co-creation [46], emotional composition [52], crafting help requests [36], and generating scientific paper ideas [30].…”

Section: Related Work 21 Ai-based Writing Tools and Human-ai Collabor...mentioning

confidence: 99%

Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models

Dhillon,

Molaei,

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Advances in language modeling have paved the way for novel human-AI co-writing experiences. This paper explores how varying levels of scaffolding from large language models (LLMs) shape the co-writing process. Employing a within-subjects field experiment with a Latin square design, we asked participants (N=131) to respond to argumentative writing prompts under three randomly sequenced conditions: no AI assistance (control), next-sentence suggestions (low scaffolding), and next-paragraph suggestions (high scaffolding). Our findings reveal a U-shaped impact of scaffolding on writing quality and productivity (words/time). While low scaffolding did not significantly improve writing quality or productivity, high scaffolding led to significant improvements, especially benefiting non-regular writers and less tech-savvy users. No significant cognitive burden was observed while using the scaffolded writing tools, but a moderate decrease in text ownership and satisfaction was noted. Our results have broad implications for the design of AI-powered writing tools, including the need for personalized scaffolding mechanisms.

show abstract

Section: Related Work 21 Ai-based Writing Tools and Human-ai Collabor...mentioning

confidence: 99%

Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models

Dhillon,

Molaei,

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…In this context, writing assistance could assist writers in conveying educational ideas in an informative and clear manner [10,85]. With entertainment as its purpose, a writing task can aim to engage and amuse readers through text, requiring coherent storytelling [133,174] to engage the audience and may use the structure of the writing itself to convey surprise [80] and pleasure [146,257]. Analytical writing provides in-depth examination, which benefits from reflection and iteration [57,113].…”

Section: Planningmentioning

confidence: 99%

“…Additionally, system-generated content may exhibit various forms of bias, ranging from skewed perspectives on topics [121,197] to societal stereotypes [106]. Lastly, the personalization of system outputs, which involves adapting to and reflecting an individual's unique writing style [80], may enhance the user's writing experience.…”

Section: Textual Diversitymentioning

confidence: 99%

A Design Space for Intelligent and Interactive Writing Assistants

Lee,

Gero,

Chung

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

show abstract

“…Prior research has supported creative writing in different ways. InkWell mimics a specified writer's personality traits and revises the draft to provide stylistic variations (Gabriel, Chen, and Nichols 2015). Metaphoria generates metaphorical connections according to the user's input to help create metaphors (Gero and Chilton 2019).…”

Section: Supporting Creative Writingmentioning

confidence: 99%

Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction

Huang¹,

Naphade²,

Laalasa³

et al. 2023

Preprint

View full text Add to dashboard Cite

Creative writing is hard: Novelists struggle with writer's block daily. While automatic story generation has advanced recently, it is treated as a "toy task" for advancing artificial intelligence rather than helping people. In this paper, we create a system that produces a short description that narrates a predicted plot using existing story generation approaches. Our goal is to assist writers in crafting a consistent and compelling story arc. We conducted experiments on Amazon Mechanical Turk (AMT) to examine the quality of the generated story plots in terms of consistency and storiability. The results show that short descriptions produced by our frame-enhanced GPT-2 (FGPT-2) were rated as the most consistent and storiable among all models; FGPT-2's outputs even beat some random story snippets written by humans. Next, we conducted a preliminary user study using a story continuation task where AMT workers were given access to machine-generated story plots and asked to write a follow-up story. FGPT-2 could positively affect the writing process, though people favor other baselines more. Our study shed some light on the possibilities of future creative writing support systems beyond the scope of completing sentences. Our code is available at: https://github.com/appleternity/Story-Plot-Generation.

show abstract

InkWell

Cited by 10 publications

References 15 publications

Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models

Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models

A Design Space for Intelligent and Interactive Writing Assistants

Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction

Contact Info

Product

Resources

About