AI Assisted Surveys I: Introduction to AI for the Survey Lifecycle
Credits:1
Grad Meth:
Reg, Aud
Prerequisite: SURV400 .
Recommended: The students should have at least one paid subscription to advanced LLM models such as the latest Gemini model, ChatGPT, or Claude, for example. We will also experiment with open-weights models such as meta.ai and others.
The course introduces the students to the latest literature and practices on AI and usage of LLMs for the survey lifecycle. We will spend time discussing how AI works, hallucinations, and review different general and task specific tools. AI desktop agents and local LLMs tools will be also reviewed. Other topics include LLMs transparency, copyright and intellectual property, and journal guidelines for publishing when AI was used in part of the writeup. Finally, we will devote time to review the latest literature on environmental concerns and the effects of long term usage of LLM tools such as the so-called "cognitive offloading". Weekly assignments will be super practical where the students will get familiarized with a large amount of AI tools, agents, and prompt techniques.