Accuracy of textual interfaces using comparative questions to elicit personal value-related information from the users for building responsible AI

Bachelor Thesis (2023)
Author(s)

B. Vizuroiu (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

C.M. Jonker – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

P.Y. Chen – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

S.D.C. Wehner – Graduation committee member (TU Delft - QID/Wehner Group)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2023
Language
English
Graduation Date
23-06-2023
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Downloads counter
259
Collections
thesis
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Individuals seeking a healthier lifestyle can benefit from behavior support agents. Customization and transparency are crucial for system effectiveness. This paper proposes using behavior trees as a user model, with a conversational agent extracting necessary information. The conversational interface enhances transparency, allowing users to understand how the system perceives them. Understanding comparative questions is vital to this approach's success. The objective is to investigate modeling personal values accurately using a conversational agent.

Technologically literate participants engaged in iterative dialogue to elicit a personalized user model. Scenarios explored the impact of contextual factors on value alignment. Results revealed decreased accuracy when more values were affected by contextual factors. Comparative questions were less effective than isolated questioning. System usability was rated poor but approaching acceptability. Larger sample sizes are needed for more comprehensive conclusions.

This research lays the foundation for conversational agents that model personal values within behavior trees, advancing behavior support systems.

Files

License info not available