Florian Lehmann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Florian Lehmann has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Buschek
University of Bayreuth
9 shared publications - Tim Zindulka
Department of Computer Science, University of Bayreuth, Bayreuth, Germany
4 shared publications - Anna Maria Feit
Saarland University, Saarland Informatics Campus, Saarbrücken, Germany
2 shared publications - Sven Goller
Department of Computer Science, University of Bayreuth, Bayreuth, Germany
2 shared publications - Albrecht Schmidt
LMU Munich
1 shared publication - Andreas Komninos
University of Patras, Patras, Greece
1 shared publication
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Collaborative Document Editing with Multiple Users and AI Agents
Current AI writing support tools are largely designed for individuals, complicating collaboration when co-writers must leave the shared workspace to use AI and then communicate and reintegrate results. We propose integrating AI agents directly into collaborative writing environments. Our prototype makes AI use visible to all users through two new shared objects: user-defined agent profiles and tasks. Agent responses appear in the familiar comment feature. In a user study (N=30), 14 teams worked on writing projects during one week. Interaction logs and interviews show that teams incorporated agents into existing norms of authorship, control, and coordination, rather than treating them as team members. Agent profiles were viewed as personal territory, while created agents and outputs became shared resources. We discuss implications for team-based AI interaction, highlighting opportunities and boundaries for treating AI as a shared resource in collaborative work.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Open AccessCollaborative Document Editing with Multiple Users and AI Agents
Current AI writing support tools are largely designed for individuals, complicating collaboration when co-writers must leave the shared workspace to use AI and then communicate and reintegrate results. We propose integrating AI agents directly into collaborative writing environments. Our prototype makes AI use visible to all users through two new shared objects: user-defined agent profiles and tasks. Agent responses appear in the familiar comment feature. In a user study (N=30), 14 teams worked on writing projects during one week. Interaction logs and interviews show that teams incorporated agents into existing norms of authorship, control, and coordination, rather than treating them as team members. Agent profiles were viewed as personal territory, while created agents and outputs became shared resources. We discuss implications for team-based AI interaction, highlighting opportunities and boundaries for treating AI as a shared resource in collaborative work.
- Open Access
- 27 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (4) , 1-26
StudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypes
Interactive systems are commonly prototyped as web applications. This approach enables studies with functional prototypes on a large scale. However, setting up these studies can be complex due to implementing experiment procedures, integrating questionnaires, and data logging. To enable such user studies, we developed the software system StudyAlign which offers: 1) a frontend for participants, 2) an admin panel to manage studies, 3) the possibility to integrate questionnaires, 4) a JavaScript library to integrate data logging into prototypes, and 5) a backend server for persisting log data, and serving logical functions via an API to the different parts of the system. With our system, researchers can set up web-based experiments and focus on the design and development of interactions and prototypes. Furthermore, our systematic approach facilitates the replication of studies and reduces the required effort to execute web-based user studies. We conclude with reflections on using StudyAlign for conducting HCI studies online.
- 27 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 9 (4) , 1-26
Open AccessStudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypes
Interactive systems are commonly prototyped as web applications. This approach enables studies with functional prototypes on a large scale. However, setting up these studies can be complex due to implementing experiment procedures, integrating questionnaires, and data logging. To enable such user studies, we developed the software system StudyAlign which offers: 1) a frontend for participants, 2) an admin panel to manage studies, 3) the possibility to integrate questionnaires, 4) a JavaScript library to integrate data logging into prototypes, and 5) a backend server for persisting log data, and serving logical functions via an API to the different parts of the system. With our system, researchers can set up web-based experiments and focus on the design and development of interactions and prototypes. Furthermore, our systematic approach facilitates the replication of studies and reduces the required effort to execute web-based user studies. We conclude with reflections on using StudyAlign for conducting HCI studies online.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Exploring Mobile Touch Interaction with Large Language Models
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Open AccessExploring Mobile Touch Interaction with Large Language Models
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Content-Driven Local Response: Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AI
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Open AccessContent-Driven Local Response: Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AI
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 264-279
An LLM-driven Transcription Task for Mobile Text Entry Studies
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 264-279
Open AccessAn LLM-driven Transcription Task for Mobile Text Entry Studies
- Open Access
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Workshop: Designing with AI-based tools
This workshop aims to explore the evolving role of AI-based tools in interaction design processes. As AI tools like Large Language Models (LLMs) become increasingly capable of generating design artefacts based on prompts, there is a compelling need to examine both their capabilities and limitations. In this workshop, we will explore and discuss the use of AI in creating interaction design artefacts, such as user scenarios, stories, and storyboards, and will critically address the challenges, including AI bias and the reduction in creative engagement. Participants will engage in evaluating AI-based tools and sharing innovative ideas. By providing a platform for both theoretical exploration and practical demonstrations, the workshop aims to foster a deeper understanding of AI’s role in design and to encourage innovative thinking about the future of technology in creative domains.
- 13 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessWorkshop: Designing with AI-based tools
This workshop aims to explore the evolving role of AI-based tools in interaction design processes. As AI tools like Large Language Models (LLMs) become increasingly capable of generating design artefacts based on prompts, there is a compelling need to examine both their capabilities and limitations. In this workshop, we will explore and discuss the use of AI in creating interaction design artefacts, such as user scenarios, stories, and storyboards, and will critically address the challenges, including AI bias and the reduction in creative engagement. Participants will engage in evaluating AI-based tools and sharing innovative ideas. By providing a platform for both theoretical exploration and practical demonstrations, the workshop aims to foster a deeper understanding of AI’s role in design and to encourage innovative thinking about the future of technology in creative domains.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Writer-Defined AI Personas for On-Demand Feedback Generation
Compelling 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.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Top Cited PapersOpen AccessWriter-Defined AI Personas for On-Demand Feedback Generation
Compelling 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.
- Top Cited PapersOpen Access
- 5 February 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 31 (2) , 1-40
The AI Ghostwriter Effect: When Users do not Perceive Ownership of AI-Generated Text but Self-Declare as Authors
Human-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 anAI 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 theAI 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.
- 5 February 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 31 (2) , 1-40
Top Cited PapersOpen AccessThe AI Ghostwriter Effect: When Users do not Perceive Ownership of AI-Generated Text but Self-Declare as Authors
Human-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 anAI 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 theAI 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.
- Open Access
- 11 September 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (MHCI) , 1-26
Typing Behavior is About More than Speed: Users' Strategies for Choosing Word Suggestions Despite Slower Typing Rates
Mobile 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.
- 11 September 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (MHCI) , 1-26
Open AccessTyping Behavior is About More than Speed: Users' Strategies for Choosing Word Suggestions Despite Slower Typing Rates
Mobile 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.
- Top Cited PapersOpen Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting
We 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 non-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.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Top Cited PapersOpen AccessChoice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting
We 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 non-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.