Weiyan Shi

2025 Early Career Fellow

Weiyan Shi is an Assistant Professor at Northeastern University, working on human-AI interaction, AI agents, and AI safety. She has been recognized as an AI2050 Early Career Fellow, MIT Technology Review’s 35 Innovators Under 35, and Rising Star awards in both Machine Learning and EECS. She has received Best Paper Nomination, Outstanding Paper, Best Social Impact Paper at ACL 2019 and ACL 2024. She co-created the first negotiation AI to achieve human-level performance in Diplomacy, with the work published in Science and featured in The New York Times, Forbes, and other major media.

AI2050 Project

If unchecked, AI’s increasing persuasive ability could lead to harmful outcomes, especially with emerging AI agents that can plan and use tools. To safeguard against this significant risk, Shi’s project addresses three critical areas: (1) investigate how AI agents might be used to persuade in potentially harmful ways, to inform better defense mechanisms; (2) develop methods to continuously monitor their evolving persuasive capabilities as an early-warning system; (3) create tools to empower users to identify and protect themselves from unwanted AI influence. Ultimately, this research aims to ensure AI develops as a trustworthy and beneficial technology for everyone.

Affiliation

Assistant Professor, Northeastern University

Hard Problem

Alignment