Ben Swanson (Research Scientist, Ubisoft)
Location: Room 2010, West Hall
Date: Tuesday, March 21
Time: 10:50 am - 11:50 am
All Access Pass, Summits Pass
Vault Recording: Video
Audience Level: All
It is the ambition of many games to create a simulation of a world containing NPCs, and in most cases these NPCs need to have something to say. They may be talking to the player, to each other, or to themselves—but they must speak without hesitation, repetition, or deviation from the narrative design.
In this session, Ben Swanson, Research Scientist at Ubisoft, will present a system that allows the narrative designer to seed their designs with first draft text that can then be accepted, edited, or regenerated by writers at the click of a button, unlocking the ability to scale up narrative systems to accompany larger and more complex worlds.
Attendees will gain an understanding of the potential for large language models as data augmentation engines, the power of using pairwise comparison as a method for evaluation of natural language generation tools, and an appreciation of not just how money can be saved but how new experiences are enabled by AI assistive tools.
This is for narrative designers, technical narrative designers, and writers—but also, more broadly, those interested in how large language models can impact the content creation pipeline.