Training Human-AI Teams
Host
David Sontag
CSAIL
Committee: David Sontag (chair, supervisor), Arvind Satyanarayan, Elena Glassman, Eric Horvitz
Zoom: https://mit.zoom.us/j/91551860173 1-2pm ET
Abstract: AI systems are augmenting humans' capabilities in settings such as healthcare and programming, forming human-AI teams. To enable more accurate and timely decisions, we need to optimize the performance of the human-AI team directly. In this thesis, we utilize a mathematical framing of the human-AI team and propose a set of methods that optimize the AI, the human, and the interface in which they communicate to enable better team performance. We first show how to provably train AI classifiers that complement humans and can defer the decision to humans when it is best to do so. However, in certain settings, AI cannot autonomously make decisions and thus only provides advice to humans. In that case, we build onboarding procedures that train humans to have an accurate mental model of the AI to enable appropriate reliance. Finally, we study how humans interact with large language models (LLMs) to write code. To understand current inefficiencies, we developed a taxonomy to categorize programmers' interactions with the LLM. Motivated by insight from the taxonomy, we leverage human feedback to know when to best display LLM suggestions.
Bio: Hussein Mozannar is a PhD student at MIT in Social & Engineering Systems and Statistics, advised by David Sontag. His research focuses on augmenting humans with AI to help them complete tasks more efficiently. Specifically, he focuses on building AI models that complement human behavior and designing interaction schemes to facilitate human-AI interaction. Applications of his research include programming (GitHub Copilot) and healthcare (radiology and maternal health).
Zoom: https://mit.zoom.us/j/91551860173 1-2pm ET
Abstract: AI systems are augmenting humans' capabilities in settings such as healthcare and programming, forming human-AI teams. To enable more accurate and timely decisions, we need to optimize the performance of the human-AI team directly. In this thesis, we utilize a mathematical framing of the human-AI team and propose a set of methods that optimize the AI, the human, and the interface in which they communicate to enable better team performance. We first show how to provably train AI classifiers that complement humans and can defer the decision to humans when it is best to do so. However, in certain settings, AI cannot autonomously make decisions and thus only provides advice to humans. In that case, we build onboarding procedures that train humans to have an accurate mental model of the AI to enable appropriate reliance. Finally, we study how humans interact with large language models (LLMs) to write code. To understand current inefficiencies, we developed a taxonomy to categorize programmers' interactions with the LLM. Motivated by insight from the taxonomy, we leverage human feedback to know when to best display LLM suggestions.
Bio: Hussein Mozannar is a PhD student at MIT in Social & Engineering Systems and Statistics, advised by David Sontag. His research focuses on augmenting humans with AI to help them complete tasks more efficiently. Specifically, he focuses on building AI models that complement human behavior and designing interaction schemes to facilitate human-AI interaction. Applications of his research include programming (GitHub Copilot) and healthcare (radiology and maternal health).