Margaret Li

770 Broadway, Facebook · New York, NY 10003 ·

Hi! I'm a research engineer at Facebook AI Research in New York. I've mostly worked on dialogue (chit-chat/open-ended), and I'm also interested in the intersection of language and RL.


Research Engineer

Facebook AI Research

August 2017 - Present

Software Engineer Intern


May 2016 - August 2016

Software Engineer Intern

January 2015 - May 2015

Data Analyst Intern


May 2014 - August 2014


Invited Lecturer

Program for Algorithmic and Combinatorial Thinking

Zero-Knowledge Proofs; Introduction to Reinforcement Learning

July 2017; July 2019

Teaching Assistant, Interim Instructor

Center for Talented Youth

Fundamentals of Computer Science

July 2017

Teaching Assistant


Combinatorics I & II

June 2017

Teaching Assistant

University of Pennsylvania

Mathematical Foundations of Computer Science
(Discrete Maths & Graph Theory)

August 2015 - May 2017

Grader and TA

Art of Problem Solving

Various courses

January 2013 - January 2017


HuaXia Chinese school

Competitive Math: AMC8 & MathCounts

August 2012 - May 2013

Private Tutor

Various students

AP subject tests, SAT prep, ESL, Secondary Math

Intermittently 2009 - 2014


University of Pennsylvania

Bachelor of Applied Sciences
Computer Science
Minor: Mathematics
August 2013 - May 2017

Homeschooled / International Academy of Beijing

August 2009 - May 2013


I love your chain mail! Making knights smile in a fantasy game world.

Shrimai Prabhumoye*, Margaret Li*, Emily Dinan, Jack Urbanek, Douwe Kiela, Jason Weston, Arthur Szlam.

Submission to ICML 2020

Don't say that! Making inconsistent dialogue unlikely with unlikelihood training.

Margaret Li, Stephen Roller, Ilia Kulikov, Sean Welleck, Spencer Poff, Emily Dinan, Y-Lan Boureau, Kyunghyun Cho, and Jason Weston.
arXiv link (pre-submission version, to be updated after anonymity period)

ACL 2020

Conversational Agents: Current Progress, Open Problems, and Future Directions.

Stephen Roller*, Y-Lan Boureau*, Jason Weston*, Antoine Bordes, Emily Dinan, Angela Fan, David Gunning, Da Ju, Margaret Li, Spencer Poff, Pratik Ringshia, Kurt Shuster, Eric Michael Smith, Arthur Szlam, Jack Urbanek, Mary Williamson.

AAAI magazine

Acute-eval: Improved dialogue evaluation with optimized questions and multi-turn comparisons.

Margaret Li, Jason Weston, and Stephen Roller.
arXiv link

NeurIPS Conversational AI Workshop 2019

Towards empathetic open-domain conversation models: A new benchmark and dataset.

Hannah Rashkin, Eric M. Smith, Margaret Li, and Y-Lan Boureau.
arXiv link

ACL 2019


When I'm not doing research, coding, or teaching, I enjoy making and eating elaborate desserts, visiting every bubble tea shop in Manhattan, singing mostly on-key, following Wikipedia tunnels, and rewatching/rereading the Lord of the Rings trilogy.

I very much like the outdoors, but only in 75-85 degree (Fahrenheit) weather. When that condition is met, I go hiking, swimming, walking, running (ok, more like jogging), and basically any other form of physical activity with low requirements on fitness and grace.