USING COMPUTATIONAL NARRATOLOGY TO ADDRESS THE ARTIFICIAL INTELLIGENCE VALUE ALIGNMENT PROBLEM
Open Access
- Author:
- Kennedy, Alayna A
- Area of Honors:
- Engineering Science
- Degree:
- Bachelor of Science
- Document Type:
- Thesis
- Thesis Supervisors:
- Dr. Lucas Jay Passmore, Thesis Supervisor
Dr. Gary L Gray, Thesis Honors Advisor - Keywords:
- Artificial intelligence
AI Safety
value alignment problem
computational narratology
narrative information extraction
narrative analysis
computational linguistics
intelligent narrative technologies
computational models of narrative
emotional arcs
natural language processing
inverse reinforcement learning - Abstract:
- This thesis provides a novel conceptual contribution to artificial intelligence (AI) safety by finding a tractable method for solving the AI value alignment problem: the creation of more complete audience models using narrative information extraction techniques from the field of computational narratology. With a thorough analysis of results from the field of computational narratology, I show that research into narrative for autonomous agents can contribute to solving the AI value alignment problem. In short, we can create artificial intelligence systems that automatically act in the best interest of humanity by teaching them to read and understand stories. The novelty of this thesis lies in the combination of two disparate academic fields: AI safety and computational narratology. Reviewing the current work and ongoing issues in both fields, I show that methods used in computational narratology to model stories can be used to solve the value alignment problem from the field of AI safety. In Chapter 2, I show why value alignment is the best solution to the problem of controlling intelligent agents. In Chapter 2, I discuss how stories encode tacit human values, and how the creation of a better audience model will contribute to solving the value alignment problem. In Chapter 3, I present two case studies providing evidence that value alignment from narrative information extraction is not only viable, but effective. Finally, I conclude by acknowledging the shortcomings of the field and pressing areas of future work.