Millicent Li

Millicent Li

I'm a third-year PhD student at Northeastern University where I'm advised by Byron Wallace. Before this, I also spent time at FAIR/Meta AI as an AI Resident, working with Marjan Ghazvininejad and Mike Lewis, and at Microsoft Research, working with Tristan Naumann.

Though I've worked on a variety of topics ranging from pretraining to information retrieval to language generation, I'm mainly interested in the intepretability of language model behaviors and generally understanding how these models work, using these insights to build better language models. To this end, I use various tools - in training and interpretability - to measure and reason about this. I'm supported by a Khoury PhD Fellowship (2022 - 2023) and an NSF GRFP (2022 - 2027).

Prior to starting my PhD, I was an undergrad at the University of Washington working with Shwetak Patel on ubiquitous computing and Noah Smith on natural language processing.

Links: CV

News

October 2024

New preprint on my paper, Multi-Field Adaptive Retrieval, done during my internship at Microsoft Semantic Machines!

August 2024

We've released a new preprint on causal interpretability, The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding of Causal Interpretability - work done with David Bau's interpretability group.

February 2024

I''ve accepted an internship offer with Microsoft Semantic Machines for the upcoming summer, working with Patrick Xia and Tongfei Chen.

January 2024

Our paper on Function Vectors in Large Language Models was accepted to ICLR 2024!

May 2023

Our paper, Summarizing, Simplifying, and Synthesizing Medical Evidence using GPT-3 (with Varying Success), was accepted to ACL 2023!

April 2022

I was awarded a 2022 NSF Graduate Research Fellowship. Northeastern wrote an article about it here.

August 2021

Started as an AI Resident with Fundamental AI Research (FAIR) at Meta in Seattle, working on natural language processing and human-computer interaction research for a year.

May 2021

Started my internship at Microsoft Research working with Tristan Naumann on the intersection of natural language processing and healthcare!

April 2021

Excited to announce that I’ll be starting my PhD in the Khoury College of Computer Sciences at Northeastern University in Boston, fall of 2022. Thanks to everyone who has supported me on this journey thus far!

March 2021

I was awarded an Honorable Mention for the 2021 NSF Graduate Research Fellowship competition.


Publications

2024

  1. Multi-Field Adaptive Retrieval
    Millicent Li, Tongfei Chen, Benjamin Van Durme, Patrick Xia
    ArXiv
  2. The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding of Causal Interpretability
    Aaron Mueller, ... Millicent Li ... Yonatan Belinkov
    ArXiv
  3. Function Vectors in Large Language Models
    Eric Todd, Millicent Li, Arnab Sen Sharma, Aaron Mueller, Byron C Wallace, David Bau
    International Conference on Learning Representations (ICLR), 2024

2023

  1. Summarizing, Simplifying, and Synthesizing Medical Evidence using GPT-3 (with Varying Success)
    Chantal Shaib, Millicent L. Li, Sebastian Joseph, Iain Marshall, Junyi Jessy Li, Byron C. Wallace
    Annual Meeting of the Association for Computational Linguistics (ACL), 2023

2022

  1. A Review on Language Models as Knowledge Bases
    Badr AlKhamissi*, Millicent Li*, Asli Celikyilmaz^, Mona Diab^, Marjan Ghazvininejad^
    arXiv
    * denotes equal contribution
    ^ denotes equal supervision

2020

  1. Multi-Channel Facial Photoplethysmography Sensing
    Parker S. Ruth, Jerry Cao, Millicent Li, Jacob E. Sunshine, Edward J. Wang, and Shwetak N. Patel
    International Conference of the IEEE Engineering in Medicine Biology Society (EMBC 2020)