The AI Memory Gap: Users Misremember What They Created With AI or WithoutAs large language models (LLMs) become embedded in interactive text generation, disclosure of AI as a source depends on people remembering which ideas or texts came from themselves and which were created with AI. We investigate how accurately people remember the source of content when using AI. In a pre-registered experiment, 184 participants generated and elaborated on ideas both unaided and with an LLM-based chatbot. One week later, they were asked to identify the source (noAI vs withAI) of these ideas and texts. Our findings reveal a significant gap in memory: After AI use, the odds of correct attribution dropped, with the steepest decline in mixed human-AI workflows, where either the idea or elaboration was created with AI. We validated our results using a computational model of source memory. Discussing broader implications, we highlight the importance of considering source confusion in the design and use of interactive text generation technologies.2026TZTim Zindulka et al.University of BayreuthHuman-LLM CollaborationExplainable AI (XAI)Privacy by Design & User ControlCHI
Exploring Mobile Touch Interaction with Large Language ModelsInteracting with Large Language Models (LLMs) for text editing on mobile devices currently requires users to break out of their writing environment and switch to a conversational AI interface. In this paper, we propose to control the LLM via touch gestures performed directly on the text. We first chart a design space that covers fundamental touch input and text transformations. In this space, we then concretely explore two control mappings: spread-to-generate and pinch-to-shorten, with visual feedback loops. We evaluate this concept in a user study (N=14) that compares three feedback designs: no visualisation, text length indicator, and length + word indicator. The results demonstrate that touch-based control of LLMs is both feasible and user-friendly, with the length + word indicator proving most effective for managing text generation. This work lays the foundation for further research into gesture-based interaction with LLMs on touch devices.2025TZTim Zindulka et al.University of BayreuthHand Gesture RecognitionHuman-LLM CollaborationCHI
CorpusStudio: Surfacing Emergent Patterns In A Corpus Of Prior Work While WritingMany communities, including the scientific community, develop implicit writing norms. Understanding them is crucial for effective communication with that community. Writers gradually develop an implicit understanding of norms by reading papers and receiving feedback on their writing. However, it is difficult to both externalize this knowledge and apply it to one's own writing. We propose two new writing support concepts that reify document and sentence-level patterns in a given text corpus: (1) an ordered distribution over section titles and (2) given the user's draft and cursor location, many retrieved contextually relevant sentences. Recurring words in the latter are algorithmically highlighted to help users see any emergent norms. Study results (N=16) show that participants revised the structure and content using these concepts, gaining confidence in aligning with or breaking norms after reviewing many examples. These results demonstrate the value of reifying distributions over other authors’ writing choices during the writing process.2025HDHai Dang et al.University of Bayreuth, HCI+AIAI-Assisted Creative WritingCreative Collaboration & Feedback SystemsCHI
Content-Driven Local Response: Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AIMobile emailing demands efficiency in diverse situations, which motivates the use of AI. However, generated text does not always reflect how people want to respond. This challenges users with AI involvement tradeoffs not yet considered in email UIs. We address this with a new UI concept called Content-Driven Local Response (CDLR), inspired by microtasking. This allows users to insert responses into the email by selecting sentences, which additionally serves to guide AI suggestions. The concept supports combining AI for local suggestions and message-level improvements. Our user study (N=126) compared CDLR with manual typing and full reply generation. We found that CDLR supports flexible workflows with varying degrees of AI involvement, while retaining the benefits of reduced typing and errors. This work contributes a new approach to integrating AI capabilities: By redesigning the UI for workflows with and without AI, we can empower users to dynamically adjust AI involvement.2025TZTim Zindulka et al.University of BayreuthVoice User Interface (VUI) DesignHuman-LLM CollaborationCHI
The AI Ghostwriter Effect: When Users do not Perceive Ownership of AI-Generated Text but Self-Declare as AuthorsHuman-AI interaction in text production increases complexity in authorship. In two empirical studies (n1 = 30 & n2 = 96), we investigate authorship and ownership in human-AI collaboration for personalized language generation. We show an AI Ghostwriter Effect: Users do not consider themselves the owners and authors of AI-generated text but refrain from publicly declaring AI authorship. Personalization of AI-generated texts did not impact the AI Ghostwriter Effect, and higher levels of participants’ influence on texts increased their sense of ownership. Participants were more likely to attribute ownership to supposedly human ghostwriters than AI ghostwriters, resulting in a higher ownership-authorship discrepancy for human ghostwriters. Rationalizations for authorship in AI ghostwriters and human ghostwriters were similar. We discuss how our findings relate to psychological ownership and human-AI interaction to lay the foundations for adapting authorship frameworks and user interfaces in AI in text-generation tasks.2024FDFiona Draxler et al.Generative AI (Text, Image, Music, Video)AI Ethics, Fairness & AccountabilityAI-Assisted Creative WritingDIS
Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI ToolsThis essay proposes and explores the concept of Collage for the design of AI writing tools, which we transfer from avant-garde literature with four facets: 1) fragmenting text in writing interfaces, 2) juxtaposing voices (content vs command), 3) integrating material from multiple sources (e.g. text suggestions), and 4) shifting from manual writing to editorial and compositional decision-making, such as selecting and arranging snippets. The essay then employs Collage as an analytical lens to analyse the user interface design of recent AI writing tools, and as a constructive lens to inspire new design directions. Finally, a critical perspective relates the concerns that writers historically expressed through literary collage to AI writing tools. In a broad view, this essay explores how literary concepts can help advance design theory around AI writing tools. It encourages creators of future writing tools to engage not only with new technological possibilities, but also with past writing innovations.2024DBDaniel BuschekGenerative AI (Text, Image, Music, Video)AI-Assisted Creative WritingDIS
Writer-Defined AI Personas for On-Demand Feedback GenerationCompelling writing is tailored to its audience. This is challenging, as writers may struggle to empathize with readers, get feedback in time, or gain access to the target group. We propose a concept that generates on-demand feedback, based on writer-defined AI personas of any target audience. We explore this concept with a prototype (using GPT-3.5) in two user studies (N=5 and N=11): Writers appreciated the concept and strategically used personas for getting different perspectives. The feedback was seen as helpful and inspired revisions of text and personas, although it was often verbose and unspecific. We discuss the impact of on-demand feedback, the limited representativity of contemporary AI systems, and further ideas for defining AI personas. This work contributes to the vision of supporting writers with AI by expanding the socio-technical perspective in AI tool design: To empower creators, we also need to keep in mind their relationship to an audience.2024KBKarim Benharrak et al.University of Texas, Austin, University of BayreuthGenerative AI (Text, Image, Music, Video)AI-Assisted Creative WritingCHI
A Design Space for Intelligent and Interactive Writing AssistantsIn 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.2024MLMina Lee et al.Microsoft ResearchHuman-LLM CollaborationAI-Assisted Creative WritingCreative Collaboration & Feedback SystemsCHI
Typing Behavior is About More than Speed: Users' Strategies for Choosing Word Suggestions Despite Slower Typing RatesMobile word suggestions can slow down typing, yet are still widely used. To investigate the apparent benefits beyond speed, we analyzed typing behavior of 15,162 users of mobile devices. Controlling for natural typing speed (a confounding factor not considered by prior work), we statistically show that slower typists use suggestions more often but are slowed down by doing so. To better understand how these typists leverage suggestions -- if not to improve their speed -- we extract eight usage strategies, including completion, correction, and next-word prediction. We find that word characteristics, such as length or frequency, along with the strategy, are predictive of whether a user will select a suggestion. We show how to operationalize our findings by building and evaluating a predictive model of suggestion selection. Such a model could be used to augment existing suggestion algorithms to consider people's strategic use of word predictions beyond speed and keystroke savings.2023FLFlorian Lehmann et al.Intelligent Voice Assistants (Alexa, Siri, etc.)Agent Personality & AnthropomorphismMobileHCI
Point of no Undo: Irreversible Interactions as a Design StrategyDespite irreversibility being omnipresent in the lifeworld, research on interactions making use of irreversibility in computing systems is still in the early stages. User freedom – provided by the undo functionality – is considered to be a pillar of "usable" computer systems, overcoming irreversibility. Within this paper, we set up a thought experiment, challenging the "undo feature" and instead take advantage of irreversibility in the interaction with physical computing systems (tangibles, robots, etc). First, we present three material speculations, each inherently utilizing irreversibility. Second, we elaborate on the concept of irreversible interactions by contextualizing our work with critical HCI discourses and deducing three design strategies. Finally, we discuss irreversibility as a design element for self-reflection, meaningful acting, and a sustainable relationship with technology. While previously individual aspects of irreversibility have been explored, we contribute a comprehensive discussion of irreversible interactions in HCI presenting artifacts, a conceptualization, design strategies, and application purposes.2023BRBeat Rossmy et al.LMU MunichPrivacy by Design & User ControlDesign FictionSustainable HCICHI
Co-Writing with Opinionated Language Models Affects Users' ViewsIf 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.2023MJMaurice Jakesch et al.Cornell University, Cornell TechHuman-LLM CollaborationAI Ethics, Fairness & AccountabilityAlgorithmic Transparency & AuditabilityCHI
Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic PromptingWe propose a conceptual perspective on prompts for Large Language Models (LLMs) that distinguishes between (1) diegetic prompts (part of the narrative, e.g. “Once upon a time, I saw a fox...”), and (2) non-diegetic prompts (external, e.g. “Write about the adventures of the fox.”). With this lens, we study how 129 crowd workers on Prolific write short texts with different user interfaces (1 vs 3 suggestions, with/out non-diegetic prompts; implemented with GPT-3): When the interface offered multiple suggestions and provided an option for diegetic prompting, participants preferred choosing from multiple suggestions over controlling them via non-diegetic prompts. When participants provided non-diegetic prompts it was to ask for inspiration, topics or facts. Single suggestions in particular were guided both with diegetic and non-diegetic information. This work informs human-AI interaction with generative models by revealing that (1) writing non-diegetic prompts requires effort, (2) people combine diegetic and non-diegetic prompting, and (3) they use their draft (i.e. diegetic information) and suggestion timing to strategically guide LLMs.2023HDHai Dang et al.University of BayreuthHuman-LLM CollaborationAI-Assisted Creative WritingCHI
Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries.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.2022HDHai Dang et al.Human-LLM CollaborationAI-Assisted Creative WritingUIST
"Your Eyes Say You Have Used This Password Before": Identifying Password Reuse from Gaze Behavior and Keystroke DynamicsA significant drawback of text passwords for end-user authentication is password reuse. We propose a novel approach to detect password reuse by leveraging gaze as well as typing behavior and study its accuracy. We collected gaze and typing behavior from 49 users while creating accounts for 1) a webmail client and 2) a news website. While most participants came up with a new password, 32% reported having reused an old password when setting up their accounts. We then compared different ML models to detect password reuse from the collected data. Our models achieve an accuracy of up to 87.7% in detecting password reuse from gaze, 75.8% accuracy from typing, and 88.75% when considering both types of behavior. We demonstrate that \revised{using gaze, password} reuse can already be detected during the registration process, before users entered their password. Our work paves the road for developing novel interventions to prevent password reuse.2022YAYasmeen Abdrabou et al.Bundeswehr University Munich, University of GlasgowEye Tracking & Gaze InteractionPasswords & AuthenticationCHI
GANSlider: How Users Control Generative Models for Images using Multiple Sliders with and without Feedforward InformationWe investigate how multiple sliders with and without feedforward visualizations influence users' control of generative models. In an online study (N=138), we collected a dataset of people interacting with a generative adversarial network (StyleGAN2) in an image reconstruction task. We found that more control dimensions (sliders) significantly increase task difficulty and user actions. Visual feedforward partly mitigates this by enabling more goal-directed interaction. However, we found no evidence of faster or more accurate task performance. This indicates a tradeoff between feedforward detail and implied cognitive costs, such as attention. Moreover, we found that visualizations alone are not always sufficient for users to understand individual control dimensions. Our study quantifies fundamental UI design factors and resulting interaction behavior in this context, revealing opportunities for improvement in the UI design for interactive applications of generative models. We close by discussing design directions and further aspects.2022HDHai Dang et al.University of BayreuthGenerative AI (Text, Image, Music, Video)Interactive Data VisualizationPrototyping & User TestingCHI
Conversations with GUIsAnnotated datasets of application GUIs contain a wealth of information that can be used for various purposes, from providing inspiration to designers and implementation details to developers to assisting end-users during daily use. However, users often struggle to formulate their needs in a way that computers can understand reliably. To address this, we study how people may interact with such GUI datasets using natural language. We elicit user needs in a survey (N=120) with three target groups (designers, developers, end-users), providing insights into which capabilities would be useful and how users formulate queries. We contribute a labelled dataset of 1317 user queries, and demonstrate an application of a conversational assistant that interprets these queries and retrieves information from a large-scale GUI dataset. It can (1) suggest GUI screenshots for design ideation, (2) highlight details about particular GUI features for development, and (3) reveal further insights about applications. Our findings can inform design and implementation of intelligent systems to interact with GUI datasets intuitively.2021KTKashyap Todi et al.Conversational ChatbotsInteractive Data VisualizationUser Research Methods (Interviews, Surveys, Observation)DIS
MEMEories: Internet Memes as Means for Daily JournalingInternet memes are (multi)media pieces, found all across the world-wide-web. Often disposing of a humorous component, they express and reflect on all kinds of local and global phenomena. Within our work, we explore how people can use internet memes to express and reflect on themselves. We built MEMEory, a mobile meme journaling app. We evaluated the prospect of meme journaling, nicknamed ''memeing'', alongside a written diary in a 2-week field study with 31 participants. Opposed to more neutral chronicle-style text entries, our results suggest that participants used memes to express specific single, rather negative events and emotions throughout the day. When reflecting on daily events, the contained emotional and often humorous connotation of memes helped participants view negative events as more positive in retrospect. Although more difficult, memeing was perceived as significantly more motivating and enjoyable. Qualitative insights show that memeing can present a fun, engaging, expressive and memorable journaling experience.2021NTNađa Terzimehić et al.Algorithmic Fairness & BiasDigital Art Installations & Interactive PerformanceInteractive Narrative & Immersive StorytellingDIS
CharacterChat: Supporting the Creation of Fictional Characters through Conversation and Progressive Manifestion with a ChatbotWe present CharacterChat, a concept and chatbot to support writers in creating fictional characters. Concretely, writers progressively turn the bot into their imagined character through conversation. We iteratively developed CharacterChat in a user-centred approach, starting with a survey on character creation with writers (N=30), followed by two qualitative user studies (N=7 and N=8). Our prototype combines two modes: (1) Guided prompts help writers define character attributes (e.g. User: "Your name is Jane."), including suggestions for attributes (e.g. Bot: "What is my main motivation?") and values, realised as a rule-based system with a concept network. (2) Open conversation with the chatbot helps writers explore their character and get inspiration, realised with a language model that takes into account the defined character attributes. Our user studies reveal benefits particularly for early stages of character creation, and challenges due to limited conversational capabilities. We conclude with lessons learned and ideas for future work.2021OSOliver Schmitt et al.Conversational ChatbotsAgent Personality & AnthropomorphismAI-Assisted Creative WritingC&C
How to Support Users in Understanding Intelligent Systems? Structuring the DiscussionThe opaque nature of many intelligent systems violates established usability principles and thus presents a challenge for human-computer interaction. Research in the field therefore highlights the need for transparency, scrutability, intelligibility, interpretability and explainability, among others. While all of these terms carry a vision of supporting users in understanding intelligent systems, the underlying notions and assumptions about users and their interaction with the system often remain unclear. We review the literature in HCI through the lens of implied user questions to synthesise a conceptual framework integrating user mindsets, user involvement, and knowledge outcomes to reveal, differentiate and classify current notions in prior work. This framework aims to resolve conceptual ambiguity in the field and enables researchers to clarify their assumptions and become aware of those made in prior work. We thus hope to advance and structure the dialogue in the HCI research community on supporting users in understanding intelligent systems.2021MEMalin Eiband et al.Explainable AI (XAI)IUI
Eliciting and Analysing Users' Envisioned Dialogues with Perfect Voice AssistantsWe present a dialogue elicitation study to assess how users envision conversations with a perfect voice assistant (VA). In an online survey, N=205 participants were prompted with everyday scenarios, and wrote the lines of both user and VA in dialogues that they imagined as perfect. We analysed the dialogues with text analytics and qualitative analysis, including number of words and turns, social aspects of conversation, implied VA capabilities, and the influence of user personality. The majority envisioned dialogues with a VA that is interactive and not purely functional; it is smart, proactive, and has knowledge about the user. Attitudes diverged regarding the assistant's role as well as it expressing humour and opinions. An exploratory analysis suggested a relationship with personality for these aspects, but correlations were low overall. We discuss implications for research and design of future VAs, underlining the vision of enabling conversational UIs, rather than single command "Q&As".2021SVSarah Theres Völkel et al.LMU MunichVoice User Interface (VUI) DesignIntelligent Voice Assistants (Alexa, Siri, etc.)Agent Personality & AnthropomorphismCHI