Although AI assistance can improve writing quality, it can also decrease feelings of ownership. Ownership in writing has important implications for attribution, rights, norms, and cognitive engagement, and designers of AI support systems may want to consider how system features may impact ownership. We investigate how the stage at which AI support for writing is provided (planning, drafting, or revising) changes ownership. In a study of short essay writing (between subjects, n = 253) we find that while any AI assistance decreased ownership, planning support only minimally decreased ownership, while drafting support saw the largest decrease. This variation maps onto the amount of text and ideas contributed by AI, where more text and ideas from AI decreased ownership. Notably, an AI-generated draft based on participants’ own outline resulted in significantly more AI-contributed ideas than AI support for planning. At the same time, more AI contributions improved essay quality. We propose that writers, educators, and designers consider writing stage when introducing AI assistance.

How might we govern a language model run for and by creative writers? While generative AI use is on the rise, many language models are created and owned in ways that limit writers’ consent, participation, and control. We report on four workshops where over one hundred creative writers came up with and analyzed metaphors for language model governance, resulting in over two hundred metaphors: objects, places, processes, groups, and infrastructure that support reasoning about language model governance. What if a language model was like a community garden? Or a seed bank? Or the bathroom in a dive bar? We report on four themes: (1) the importance of consent, (2) how to define community boundaries, (3) ways to give contributor recognition, and (4) trade-offs in scale of language models. These metaphors point towards smaller, open models that encode group values. We discuss concrete ways to make community language models a reality.

As generative AI tools become embedded in creative practice, questions of ownership in co-creative contexts are pressing. Yet studies of human-AI collaboration often invoke "ownership" without definition: sometimes conflating it with other concepts, and other times leaving interpretation to participants. This inconsistency makes findings difficult to compare across or even within studies. We introduce a framework of creative ownership comprising three dimensions - Person, Process, and System - each with three subdimensions, offering a shared language for both system design and HCI research. In semi-structured interviews with 21 creative professionals, we found that participants’ initial references to ownership (e.g., embodiment, control, concept) were fully encompassed by the framework, demonstrating its coverage. Once introduced, however, they also articulated and prioritized the remaining subdimensions, underscoring how the framework expands reflection and enables richer insights. Our contributions include 1) the framework, 2) a web-based visualization tool, and 3) empirical findings on its utility.

Artificial intelligence (AI)-infused systems can offer valuable assistance to writers, but they may also produce imperfect or unsatisfactory suggestions that require efficient correction. Word choice presents a challenge for writers that can be addressed by several tools, but these systems typically require users to switch browser tabs or tools and break their flow of thinking, or otherwise fail to incorporate the context associated with users' writing or their intentions, leaving them with subpar or unrelated suggestions. We present SYNthia, a word-suggestion interface that allows users to be directly involved in the suggestion generation process by providing natural language feedback. We performed two pilot qualitative studies, finding that SYNthia provided users with a more practical interface that (1) allowed them to receive their target word more efficiently, (2) eliminated the need to for users switch contexts (e.g. switching tabs or devices), and (3) improved users' perceived quality of writing. In addition, we performed a formal user study comparing how novice and expert writers interact with SYNthia different, ultimately concluding that the writing level had no quantitatively significant impact on interactions with the tool, raising more questions for further study. However, the qualitative study surfaced several interesting observations regarding how writers interact with an AI-powered thesaurus, making progress towards the greater goal of integrating AI in the writing process while maintaining human agency and ownership. All code for this project can be found at the Github repository: https://github.com/AEst2002/word-suggester/tree/thesis.

Peer Reviewed

Generative AI brings novel and impressive abilities to help people in everyday tasks. There are many AI workflows that solve real and complex problems by chaining AI outputs together with human interaction. Although there is an undeniable lure of AI, it is uncertain how useful generative AI workflows are after the novelty wears off. Additionally, workflows built with generative AI have the potential to be easily customized to fit users’ individual needs, but do users take advantage of this? We conducted a three-week longitudinal study with 12 users to understand the familiarization and customization of generative AI tools for science communication. Our study revealed that there exists a familiarization phase, during which users were exploring the novel capabilities of the workflow and discovering which aspects they found useful. After this phase, users understood the workflow and were able to anticipate the outputs. Surprisingly, after familiarization the perceived utility of the system was rated higher than before, indicating that the perceived utility of AI is not just a novelty effect. The increase in benefits mainly comes from end-users’ ability to customize prompts, and thus potentially appropriate the system to their own needs. This points to a future where generative AI systems can allow us to design for appropriation.

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 community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions and codes by systematically reviewing 115 papers, while leveraging the expertise of researchers in various disciplines. 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 design of new writing assistants.

Large language models (LLMs) are capable of generating multiple responses to a single prompt, yet little effort has been expended to help end-users or system designers make use of this capability. In this paper, we explore how to present many LLM responses at once. We design five features, which include both pre-existing and novel methods for computing similarities and differences across textual documents, as well as how to render their outputs. We report on a controlled user study (n=24) and eight case studies evaluating these features and how they support users in different tasks. We find that the features support a wide variety of sensemaking tasks and even make tasks tractable that our participants previously considered to be too difficult to attempt. Finally, we present design guidelines to inform future explorations of new LLM interfaces.

New capabilities in foundation models are owed in large part to massive, widely-sourced, and under-documented training data collections. Existing practices in data collection have led to challenges in tracing authenticity, verifying consent, preserving privacy, addressing representation and bias, respecting copyright, and overall developing ethical and trustworthy foundation models. In response, regulation is emphasizing the need for training data transparency to understand foundation models’ limitations. Based on a large-scale analysis of the foundation model training data landscape and existing solutions, we identify the missing infrastructure to facilitate responsible foundation model development practices. We examine the current shortcomings of common tools for tracing data authenticity, consent, and documentation, and outline how policymakers, developers, and data creators can facilitate responsible foundation model development by adopting universal data provenance standards.

Recently, large language models have made huge advances in generating coherent, creative text. While much research focuses on how users can interact with language models, less work considers the social-technical gap that this technology poses. What are the social nuances that underlie receiving support from a generative AI? In this work we ask when and why a creative writer might turn to a computer versus a peer or mentor for support. We interview 20 creative writers about their writing practice and their attitudes towards both human and computer support. We discover three elements that govern a writer’s interaction with support actors: 1) what writers desire help with, 2) how writers perceive potential support actors, and 3) the values writers hold. We align our results with existing frameworks of writing cognition and creativity support, uncovering the social dynamics which modulate user responses to generative technologies.

Handwriting recognition is improving in leaps and bounds, and this opens up new opportunities for stylus-based interactions. In particular, note-taking applications can become a more intelligent user interface, incorporating new features like autocomplete and integrated search. In this work we ran a gesture elicitation study, asking 21 participants to imagine how they would interact with an imaginary, intelligent note-taking application. Participants were prompted to produce gestures for common actions such as select and delete, as well as less common actions (for gesture interaction) such as autocomplete accept/reject, ‘hide’, and search. We report agreement on the elicited gestures, finding that while existing interactions are prevalent (like double taps and long presses) a number of more novel interactions (like dragging selected items to hotspots or using annotations) were also well-represented. We discuss the mental models participants drew on when explaining their gestures and what kind of feedback users might need to move to more stylus-centric interactions.

Large-scale language models are rapidly improving, performing well on a wide variety of tasks with little to no customization. In this work we investigate how language models can support science writing, a challenging writing task that is both open-ended and highly constrained. We present a system for generating “sparks”, sentences related to a scientific concept intended to inspire writers. We find that our sparks are more coherent and diverse than a competitive language model baseline, and approach a human-written gold standard. We run a user study with 13 STEM graduate students writing on topics of their own selection and find three main use cases of sparks—inspiration, translation, and perspective—each of which correlates with a unique interaction pattern. We also find that while participants were more likely to select higher quality sparks, the average quality of sparks seen by a given participant did not correlate with their satisfaction with the tool. We end with a discussion about what impacts human satisfaction with AI support tools, considering participant attitudes towards influence, their openness to technology, as well as issues of plagiarism, trustworthiness, and bias in AI.

Improvements in natural language processing and generation have made possible new and powerful creativity support tools for creative writers. However, it remains unclear how professional writers themselves might want to integrate technology into their existing writing practices. In this work we ran an elicitation study, asking 14 professional poets to consider how they would make use of computation in the context of a custom, interactive writing interface or “Poetry Machine.” We found that the poets desired a wide range of functions, from presenting auditory responses to deleting random words. We also found that many poets did not simply report what their ideal interface would do but rather contextualized their designs by describing why they are artistically meaningful, sometimes with respect to specific literary influences and traditions. We present an initial analysis of the elicitation study and observe some differences between the Poetry Machine designs and existing creativity support tools. This study lays the groundwork for a second phase where we will build a selection of the machines and study how the poets use them over time.

As more and more forms of AI become prevalent, it becomes increasingly important to understand how people develop mental models of these systems. In this work we study people's mental models of an AI agent in a cooperative word guessing game. We run a study in which people play the game with an AI agent while ``thinking out loud''; through thematic analysis we identify features of the mental models developed by participants. In a large-scale study we have participants play the game with the AI agent online and use a post-game survey to probe their mental model. We find that those who win more often have better estimates of the AI agent's abilities. We present three components---global knowledge, local knowledge, and knowledge distribution---for modeling AI systems and propose that understanding the underlying technology is insufficient for developing appropriate conceptual models---analysis of behavior is also necessary.

People are increasingly getting information and news from social media. On Twitter we are seeing the emergence of "tweetorials" -- long, explanatory Twitter threads written by experts. In this work we study tweetorials as a form of science writing. While scientists have begun to champion the importance of Twitter as a science communication medium, few have studied how people are successfully using this medium to communicate complex and nuanced ideas. To understand how tweetorials work, we curated a collection of 46 clear and engaging tweetorials from multiple domains. We analyzed these tweetorials for the writing techniques that they employ, and found that while tweetorials use many traditional science writing techniques, they also use more subjective language, actively build credibility, and incorporate media in unique ways. In addition, we report on a workshop we ran to aid science PhD students in writing tweetorials, and find that while providing common tweetorial techniques improves their writing, the students still struggle to balance their scientific sensibilities with the informal tone associated with tweetorials. We discuss the implications of using informal and subjective language in science communication, as well as how technology can support scientists in writing tweetorials.

As more and more forms of AI become prevalent, it becomes increasingly important to understand how people develop mental models of these systems. In this work we study people's mental models of AI in a cooperative word guessing game. We run think-aloud studies in which people play the game with an AI agent; through thematic analysis we identify features of the mental models developed by participants. In a large-scale study we have participants play the game with the AI agent online and use a post-game survey to probe their mental model. We find that those who win more often have better estimates of the AI agent's abilities. We present three components for modeling AI systems, propose that understanding the underlying technology is insufficient for developing appropriate conceptual models (analysis of behavior is also necessary), and suggest future work for studying the revision of mental models over time.

Writers regularly use a thesaurus to help them write well; the thesaurus is one of the few widespread writing support tools and many writers find it integral to their writing practice. A normal thesaurus is hand-crafted and structured around strict synonymy for a given word sense. However, writers rarely look for a perfectly synonymous word -- instead they have additional ideas or constraints, such as words that are less cliche, more specific, or less gendered. Poets describe their usage as searching for words that "hold more interesting connotations." We present a machine learning approach to thesaurus generation, using word embeddings, that leverages stylistically distinct corpora -- such as naturalist writing, novels by a particular author, or writing from a technical discipline. We show examples of how stylistic thesauruses differ from each other and from a regular thesaurus, as well as preliminary responses from two writers who are given multiple stylistic thesauruses. Writers describe these thesauruses as reflective of style, unique from each other, and more exploratory and associative than a regular thesaurus. They also describe an increased attention to connotation. We outline plans for quantitative evaluation of stylistic thesauruses, and user studies to understand their impact on specific tasks.

Creative writing, from poetry to journalism, is at the crux of human ingenuity and social interaction. Existing creative writing support tools produce entire passages or fully formed sentences, but these approaches fail to adapt to the writer's own ideas and intentions. Instead we posit to build tools that generate ideas coherent with the writer's context and encourage writers to produce divergent outcomes. To explore this, we focus on supporting metaphor creation. We present Metaphoria, an interactive system that generates metaphorical connections based on an input word from the writer. Our studies show that Metaphoria provides more coherent suggestions than existing systems, and supports the expression of writers' unique intentions. We discuss the complex issue of ownership in human-machine collaboration and how to build adaptive creativity support tools in other domains.

Despite the success of style transfer in image processing, it has seen limited progress in natural language generation. Part of the problem is that content is not as easily decoupled from style in the text domain. Curiously, in the field of stylometry, content does not figure prominently in practical methods of discriminating stylistic elements, such as authorship and genre. Rather, syntax and function words are the most salient features. Drawing on this work, we model style as a suite of low-level linguistic controls, such as frequency of pronouns, prepositions, and subordinate clause constructions. We train a neural encoder-decoder model to reconstruct reference sentences given only content words and the setting of the controls. We perform style transfer by keeping the content words fixed while adjusting the controls to be indicative of another style. In experiments, we show that the model reliably responds to the linguistic controls and perform both automatic and manual evaluations on style transfer. We find we can fool a style classifier 84% of the time, and that our model produces highly diverse and stylistically distinctive outputs. This work introduces a formal, extendable model of style that can add control to any neural text generation system.

Hyper-redundant manipulators can be fragile, expensive, and limited in their flexibility due to the distributed and bulky actuators that are typically used to achieve the precision and degrees of freedom (DOFs) required. Here, a manipulator is proposed that is robust, high-force, low-cost, and highly articulated without employing traditional actuators mounted at the manipulator joints. Rather, local tunable stiffness is coupled with off-board spooler motors and tension cables to achieve complex manipulator configurations. Tunable stiffness is achieved by reversible jamming of granular media, which—by applying a vacuum to enclosed grains—causes the grains to transition between solid-like states and liquid-like ones. Experimental studies were conducted to identify grains with high strength-to-weight performance. A prototype of the manipulator is presented with performance analysis, with emphasis on speed, strength, and articulation. This novel design for a manipulator—and use of jamming for robotic applications in general—could greatly benefit applications such as human-safe robotics and systems in which robots need to exhibit high flexibility to conform to their environments.