UiB AI #12: Aligning AI with Human Values. Challenges and Solutions
Arrangementet samler eksperter, forskere og bransjefolk for å utforske, diskutere og fremme vår forståelse av utfordringene og løsningene knyttet til å tilpasse kunstig intelligens-systemer til menneskelige verdier og mål. Det foregår i sin helhet på engelsk.
Hovedinnhold
The event brings together experts, researchers, and industry professionals to explore, discuss, and advance our understanding of the challenges and solutions related to aligning artificial intelligence systems with human values and goals.
If you cannot attend in person, you can watch the seminar through this link.
The objectives and expected outcomes of this seminar are as follows:
- Participants will gain a deeper understanding of the challenges associated with AI alignment, including biases, interpretability, and value misalignment.
- The seminar will facilitate interactive discussions to develop concrete solutions and strategies for addressing AI alignment challenges.
- Participants will have the opportunity to network with leading experts and build connections that can lead to ongoing collaborations and partnerships
This event is a collaboration between Universitetsfondet and UiB AI.
Programme:
09:00-09:30: Registration and coffee
09:30-09:40: Introduction by moderator Samia Touileb, Department of Information Science and Media Studies at University of Bergen
09:40-10:15: How can we prevent LLMs from behaving badly? Jan Broersen, Professor at the Department of Philosophy and Religious Studies, Utrecht University
10:15-10:50: AI alignment of LLMs: a simple case study on detecting deceptive designs. Davide Liga, Post. Doc. at the Faculty of Science, Technology and Medicine, Université de Luxembourg
10:50-11:05: Coffee break
11:05-11:40: Value aware AI. Nardine Osman, Tenured Scientist at the Artificial Intelligence Research Institute (IIIA), Spanish National Research Council (CSIC) (presentation by Zoom)
11:40-12:15: Human Interactions and their Implications for Ethical and Responsible Robotics and AI. Dr. Emily C. Collins, Dame Kathleen Ollerenshaw Fellow at the Department of Computer Science, The University of Manchester.
12:15-12:45: Lunch (included)
12:45-13:20: Towards a Critical Political Economy of Generative AI. Vinit Ravishankar, Independent researcher with a PhD in multilingual language technology
13:20-13:55: Enabling Responsible AI with Humans. Nadin Kokciyan, Director of the Human-Centered AI Lab (CHAI Lab) at the University of Edinburgh
13:55-1410: Coffee break
14:10-14:45: News in AI age: alignment with editorial values and ethics. Anastasiia Klimashevskaia, PhD candidate, MediaFutures: Research Centre for Responsible Media Technology & Innovation
14:45-15:20: Machine ethics and alignment. Marija Slavkovik, Professor at Department of Information Science and Media Studies at the University of Bergen
15:20-15:40: Wrap up and discussions