Academic activities

Talks, Teaching & Service

Selected invited talks, teaching and mentorship activities, and service to the research community.

Invited talks & lectures

Morals, Values & Ethics in AI Alignment.

UC Berkeley EECS Seminar (taught by Anca Dragan). · October 2026.

Slides

Understanding & Mitigating Safety Risks in Large Language Models.

Pomona University · October 2025.

Slides

Towards Understanding the (Conceptual) Structure of LLMs

CogSci Workshop · 2024

Slides

Language Grounding

Brown University, CSCI 1460 (Taught by Ellie Pavlick) · November 2023

Slides

Using Insights from Human Language for Multi-agent Decision Making

DIMACS · October 2023

Slides

Intro to AI Safety

M2L Summer School · September 2024

Slides

Intro to Language Models and Ethics

M2L Summer School · September 2022

Slides

Academic service

Senior Area Chair

EMNLP 2026, ACL 2026, EMNLP 2025, ICLR 2025, ACL 2025, NAACL 2025

Area Chair

NAACL 2025, ICLR 2025, NeuRIPs 2026, NeuRIPs 2025, ACL 2024, EMNLP 2024 (previous years excluded)

Reviewing

Journals: CL, TACL, TMLR, JMLR; ConferenceL FaccT, CHI, ICML and select others.

Tutorials

LLMs and Vision at ACL · 2023