Trust in Large Language Model chatbots depends not only on what these systems do but also on how their behavior is governed and communicated. We present Trust Mediator, a workbench that supports service owners in authoring and assessing principle sets for LLM-driven chatbots through persona-based exploration and structured scaffolds. To examine this workflow, we use three analytic lenses—specificity, coverage, and coherence—to characterize the principles produced. In an exploratory between-subjects study, we compared manual and assisted principle authoring. Participants in both conditions viewed principles as useful for governing and assessing chatbot behavior. Assisted authoring was generally perceived as more supportive and tended to broaden coverage. Manual authoring required more effort but yielded principles that were significantly more specific. These findings highlight complementary strengths of assisted and manual pathways, illustrating the value of treating principle sets as design objects within governance workflows. Beyond their analytic role in this study, the lenses also suggest opportunities for supporting the construction and inspection of principle sets.

Robots are increasingly present in spaces inhabited by humans. From a privacy-sensitive design perspective, they present challenges, as they acquire data about their environment to act autonomously and interact with their users. This may raise privacy concerns among robot users and bystanders. To address these concerns, we propose a multi-touchpoint design enabling users and bystanders to investigate how their privacy is protected. These touchpoints include (1) embodied interaction with the robot, either directly, whenever encountering a robot, or (2) later, in a dedicated physical space, (3) interaction with a virtual AI chatbot through a web site, and (4) interaction with a human Data Protection Officer. We evaluated this design and the usefulness of the proposed touchpoints in two studies. Our findings are threefold: first, all touchpoints are useful and complement each other; second, different people have different preferences; and third, the attributes of the situation (i.e. location, busyness, contextuality and sensitivity) impact the choice of the touchpoint they would use to ask their questions.

Various strategies have been explored for robots to prevent navigation blocks. However, such blocks may still happen and robots then need to resolve them. Blocks may happen either on the robot’s path or target location and may be caused either by human or object obstacles. In this paper we explore the design of robot behaviors to resolve such navigation blocks by asking humans for help. These behaviors combine different communication modalities in steps with increasing urgency. We focus on robots with limited sensing capabilities and present findings from an in-person experiment evaluating these behaviors. Our findings illustrate that humans can be more easily engaged to solve blocks caused by themselves rather than by third party objects. They also highlight the complexity of having robots with limited sensing capabilities successfully enact sequential interactions with their bystanders.

As robots increasingly share spaces with people, it becomes important for them to behave according to our social norms. In this paper, we explore the problem of finding socially acceptable locations for a robot to wait for a shared elevator by learning from expert annotations. Access to relevant, unlabeled data is however scarce in this setting and annotations expensive to gather, as they require explicit knowledge about the social norms, the robot, and the service it carries out. We tackle this low-data regime as follows. First, we use Procedural Content Generation to generate plausible waiting scenes to be annotated. Second, we leverage available sociological studies and operationalize relevant social norms as feature maps. We train a variety of models with only 125 procedurally-generated expert-annotated scenes, testing the impact of the proposed feature maps. In our ablation study, the feature maps help the models’ performance and their generalization capabilities to non-synthetic, real scenes. We inspect the decisions taken by the best models, probing their strengths and weaknesses, and identifying general issues and discussing potential solutions.

Robots powered by Artificial Intelligence require continuous sensing to function and interact autonomously with their environment. This may create concerns for their users. Here, we describe a study in the context of an office environment equipped with autonomous delivery robots. Our study aims to understand the employees’ current comprehension of the data captured by the robots, the nature of their concerns and ways to mitigate those. We found that the employees have little knowledge about data capture and that providing such knowledge can go either way, reassuring or generating new concerns which are often contextual. We qualitatively analysed reasons for having or not having concerns. Our findings include that trust in the employer is an important factor limiting them.

This paper examines the advantages and disadvantages of combining Human-Like and Machine-Like behaviors for a robot taking a shared elevator with a bystander as part of an office delivery service scenario. We present findings of an in-person wizard-of-oz experiment that builds on and implements behavior policies developed in a previous study. In this experiment, we found that the combination of Machine-Like and Human-Like behaviors was perceived as better than Human-Like behaviors alone. We discuss possible reasons and point to key capabilities that a socially competent robot should have to achieve better Human-Like behaviors in order to seamlessly negotiate a social encounter with bystanders in a shared elevator or similar scenario. We found that establishing and maintaining a shared transactional space is one of these key requirements.

Runners want to actively explore unknown environments without the fear of getting lost. We conducted a survey to better understand runners’ needs and practices in this context. The survey results emphasized the interest in flexible exploration. To address this interest, we designed FlexNav, a system that supports exploratory running through flexible tours that link the best runnable zones in a neighbourhood. FlexNav provides adaptive navigation support enabling runners to follow such tours without continually getting disruptive directions. We tested it with runners to assess its usability. The results confirm the usefulness of the system and the users' preference for flexible tours over fully specified tours with turn-by-turn guidance. Our study highlights the subjective nature of runnable zones and the subtle balance between guidance and exploration.

Navigation systems for runners commonly provide turn-by-turn directions via voice and/or map-based visualizations. While voice directions require permanent attention, map-based guidance requires regular consultation. Both disrupt the running activity. To address this, we designed RunAhead, a navigation system using head scanning to query for navigation feedback, and we explored its suitability for runners in an outdoor experiment. In our design, we provide the runner with simple and intuitive navigation feedback on the path s/he is looking at through three different feedback modes: haptic, music and audio cues. In our experiment, we compare the resulting three versions of RunAhead with a baseline voice-based navigation system. We find that demand and error are equivalent across all four conditions. However, the head scanning based haptic and music conditions are preferred over the baseline and these preferences are impacted by runners' habits. With this study we contribute insights for designing navigation support for runners.

Crowdsourcing is a relatively new model of labor where both the workers and work providers are experiencing its growing pains. A dominant platform that implements this model of labor is Amazon Mechanical Turk (AMT). While AMT has evolved over the years, the changes have focused mainly on work providers and have not addressed the problems workers face (e.g. dealing with market volatility and unpaid time searching for work). In this paper we present emph{TurkBench}, a tool meant to provide workers with personalized market visualization and session management. We discuss the design philosophy of the tool, briefly discuss four Turkers' reaction to a demo, and outline future work.

To face ongoing global warming issues and in general to promote sustainable development, a number of tools have been developed that help people to assess the impact of their behavior on the environment. In this paper we present the Personal Assessment Tool, a system that observes print behavior and aggregates information in ways meant to promote more conscious use of the shared printing resources.

This paper describes how achieving consistent colour reproduction across different devices is a complicated matter. Although there is a technological infrastructure for managing colour across devices this is very rarely used as intended. This infrastructure has been created by modelling the problem of colour management as a wholly technical one. In this paper we illustrate the importance of understanding the management of colour as a socio-technical problem, by describing the findings of a multi-sited ethnography of designers and print shops. Our analysis of the ethnography reveals that designers build up practical, tangible, visual understandings of colour and that these do not fit with the current solution, which requires users to deal with colour in an abstract manner. This paper builds on previous research in CSCW which has considered the importance of socio-technical systems, bringing the work into a previously unexplored domain. It shows how an understanding of the social can also be central when designing technical infrastructures.

This article illustrates how to easily address scalability issues within distributed applications built on top of the Coordination Language Facility (CLF) middleware. CLF provides a distributed object computing framework with high expressiveness, flexibility and dynamicity. Our solutions rely on a core set of techniques such as replication, caching and distribution. We decline them along a geographical, a numerical, and an administrative dimension. We illustrate our approach with examples taken from Yaka, an application in the field of knowledge management and document awareness. In the context of this application we show in detail how the coordination model of the CLF and its associated scripting language enable straightforward solutions to various scalability issues.

CLF/Mekano is a distributed object infrastructure oriented towards the high-level coordination of coarse grain components. Unlike other infrastructures of the same class, such as CORBA or DCOM, coordination in CLF/Mekano is built-in at the lowest level, namely at the inter-component communication protocol level, and not as a side service (such as the event, transaction or negotiation services of Corba). Although the CLF protocol is "lightweight" (it relies on very few concepts and only 8 communication "verbs"), it makes the design and implementation of components more complex, but also more valuable if it can be reused. The Mekano library has been developed in order to deal with this complexity, targeting reusability. It provides ready-to-use generic classes of customizable components, as well as useful component parts which can be reassembled according to application specific needs. Of course, further layers of domain-specific libraries (so called business object libraries), can then be developed on top of Mekano, to provide ready-to-use components dedicated to specific business needs (in the line of Enterprise Java Beans).

Summary form only given. The amount of information available from electronic sources on the World Wide Web and other on-line information repositories is highly heterogeneous and increasing dramatically. Tools are needed to extract relevant information from these repositories. The Constraint-Based Knowledge Brokers project (CBKB) at RXRC Grenoble realizes sophisticated facilities for efficient information retrieval, schema integration, and knowledge fusion. The current implementation of the CBKB research prototype involves three kinds of agents: a) users, who input queries and process answers (i.e., ranking, fusion) through a GUI; b) wrappers, capable of interrogating heterogeneous information sources, which can provide answers to elementary queries (essentially various public bibliographic catalogues available on the Web, as well as preprint archives and opera information repositories); c) brokers, which can manage complex queries (i.e., decompose a complex query, recompose the partial answers, synthesize a full answer) and which mediate between the GUI and the different wrappers. The core of the system is given by the brokers, which provide various important services such as intelligent caching, filtering and knowledge combination. Requests, intermediate information, and results are internally represented via feature constraints. Requests do not need to be fully defined; they may correspond to partial specifications of the requested information.

In order to solve real world problems, knowledge-based systems must rely upon knowledge about the factual entities involved, about algorithmic methods which use, transform or produce these entities and about the ways these methods should be chained up according to identified problem solving strategies. These strategies are complex to represent. An object-oriented task model is therefore presented and discussed. A task-engine has been developed to solve problems exploiting this model.