CS&E Colloquium: Towards Planning in Creative Contexts

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m. This week's speaker, Alexander Spangher (University of Southern California), will be giving a talk titled "Towards Planning in Creative Contexts".

Abstract

Recent modeling innovations that teach large language models (LLMs) how to plan — or break down and solve complex problems into multiple steps — have allowed LLMs to achieve impressive results in domains like mathematical problem-solving and coding. However, tasks in such domains are often characterized by large training datasets and well-defined rewards. Many human-centered tasks, especially creative tasks, occur in contexts where goals and rewards are not as clearly defined and datasets are limited: thus, we lack the means necessary to train models to plan in such settings. In this talk, I will outline a research agenda that can enable us to make progress. I will show three pillars: (1) observing plans: how long-range text modeling can help us make inferences about past human actions based on state-observations (a process known to cognitive psychologists as "emulation, based on end-state observation"); (2) improving plans: how these inferences can help us benchmark LLMs in creative tasks and how hierarchical modeling can help us learn novel planning strategies; and (3) executing plans: how classifier-free guidance, an inference-time technique, can be utilized to help LLMs adhere to complex plans. I will demonstrate these processes in the domain of journalism, with specific focus on the task of helping journalists find sources to support their writing processes.

Biography