Trust in Large Language Model (LLM) 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 enables service owners to elicit chatbot principles and run persona-driven evaluations. To assess this approach, we introduce three analytic metrics: specificity, coverage, and coherence.
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, with trends toward greater coherence and improvements in chatbot responses.
These findings highlight the complementary strengths of assisted and manual pathways. Beyond their analytic role in this study, the metrics themselves point to future use as design objects for principle-authoring tools.
Surfacing governing principles for chatbots: A workbench and comparative study
| Antonietta Grasso, Jisun Park, Jutta Willamowski, Laurent Besacier, Jos Rozen |
| The ACM conference on Human Factors in Computing Systems (CHI), Barcelona, Spain, 13–17 April, 2026 |
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.