Information disorder — including misinformation, disinformation, and malinformation — continues to undermine public discourse. Large language model (LLM)-based browser extensions show promise as tools for intervention, yet the role of publicly available tools in this space is not well understood. We conducted a scoping review of the Chrome Web Store and Firefox Add-Ons Store (May–July 2025), screening 951 records and including 34 extensions that use LLMs to process webpage content or user input. Through thematic analysis, we identified six interaction design concept categories: Extension Access, Display Mode, User Guidance, Customization, Content Understanding & Manipulation, and Navigation & Utilities. While extensions demonstrated diverse functionality and potential to debunk information disorder, they overwhelmingly operated as reactive tools, requiring explicit user initiation. Moreover, they rarely embedded themselves within webpage context. These findings reveal a “proactive gap” in current designs. Future LLM-powered extensions should move beyond responsiveness toward proactive, context-aware interventions that inoculate users against misinformation and strengthen critical thinking.

We present FallacyCheck, a proactive Large Language Model (LLM)-based browser extension designed to motivate the critical assessment of news articles by questioning logical fallacies. Existing LLM-based extensions are reactive, limiting their ability to inoculate users against information disorder. FallacyCheck overcomes this by proactively identifying logical fallacies, such as "Appeal to Emotion" and "Ad Hominem", and most importantly, motivating users to critically assess the article by posing them a thought-provoking, non-leading question in a contextual tooltip. This design, rooted in inoculation theory, prompts users toward meta-cognitive reflection on the argument’s logical structure. A preliminary evaluation with 16 highschool students showed the tool was perceived to be easy to use, and the questions helped to stimulate critical thinking. Crucially, participants generally would not have posed these critical questions without the tool’s support.

Research on transparency tools for information privacy has largely focused on users' perceptions of their usefulness-showing users prefer aggregated forms of data representation (e.g., interest segments) over hard-to-interpret raw data.However, users still do not understand what to learn from such interest segments.Representing a user's digital footprint as a user persona may serve as an effective way to communicate such information.Large Language Models (LLMs) show promise in dynamically presenting information in a way that can change user perceptions of complex issues-including privacy, personal data disclosure and user persona generation.We present PERSONÆR-a browser extension for LLM-based user persona generation from live website visits. CCS Concepts• Security and privacy → Usability in security and privacy; Social aspects of security and privacy; • Human-centered computing → Empirical studies in HCI.

With the ongoing efforts to empower people with mobility impairments and the increase in technological acceptance by the general public, assistive technologies, such as collaborative robotic arms, are gaining popularity. Yet, their widespread success is limited by usability issues, specifically the disparity between user input and software control along the autonomy continuum. To address this, shared control concepts provide opportunities to combine the targeted increase of user autonomy with a certain level of computer assistance. This paper presents the free and open-source AdaptiX XR framework for developing and evaluating shared control applications in a high-resolution simulation environment. The initial framework consists of a simulated robotic arm with an example scenario in Virtual Reality (VR), multiple standard control interfaces, and a specialized recording/replay system. AdaptiX can easily be extended for specific research needs, allowing Human-Robot Interaction (HRI) researchers to rapidly design and test novel interaction methods, intervention strategies, and multi-modal feedback techniques, without requiring an actual physical robotic arm during the early phases of ideation, prototyping, and evaluation. Also, a Robot Operating System (ROS) integration enables the controlling of a real robotic arm in a PhysicalTwin approach without any simulation-reality gap. Here, we review the capabilities and limitations of AdaptiX in detail and present three bodies of research based on the framework. AdaptiX can be accessed at https://adaptix.robot-research.de.

Robotic solutions, in particular robotic arms, are becoming more frequently deployed for close collaboration with humans, for example in manufacturing or domestic care environments. These robotic arms require the user to control several Degrees-of-Freedom (DoFs) to perform tasks, primarily involving grasping and manipulating objects. Standard input devices predominantly have two DoFs, requiring time-consuming and cognitively demanding mode switches to select individual DoFs. Contemporary Adaptive DoF Mapping Controls (ADMCs) have shown to decrease the necessary number of mode switches but were up to now not able to significantly reduce the perceived workload. Users still bear the mental workload of incorporating abstract mode switching into their workflow. We address this by providing feed-forward multimodal feedback using updated recommendations of ADMC, allowing users to visually compare the current and the suggested mapping in real-time. We contrast the effectiveness of two new approaches that a) continuously recommend updated DoF combinations or b) use discrete thresholds between current robot movements and new recommendations. Both are compared in a Virtual Reality (VR) in-person study against a classic control method. Significant results for lowered task completion time, fewer mode switches, and reduced perceived workload conclusively establish that in combination with feedforward, ADMC methods can indeed outperform classic mode switching. A lack of apparent quantitative differences between Continuous and Threshold reveals the importance of user-centered customization options. Including these implications in the development process will improve usability, which is essential for successfully implementing robotic technologies with high user acceptance.

Nowadays, robots collaborate closely with humans in a growing number of areas. Enabled by lightweight materials and safety sensors, these cobots are gaining increasing popularity in domestic care, supporting people with physical impairments in their everyday lives. However, when cobots perform actions autonomously, it remains challenging for human collaborators to understand and predict their behavior. This, however, is crucial for achieving trust and user acceptance. One significant aspect of predicting cobot behavior is understanding their motion intent and comprehending how they ”think” about their actions. We work on solutions that communicate the cobots AI-generated motion intent to a human collaborator. Effective communication enables users to proceed with the most suitable option. We present a design exploration with different visualization techniques to optimize this user understanding, ideally resulting in increased safety and end-user acceptance.