Hi! I am a PhD candidate at MIT CSAIL, affiliated with the language & intelligence (LINGO) lab @ MIT. My advisor is Jacob Andreas. I have very broad interests within natural language processing, but some high-level themes of recent work include:

• Probing for and improving representations of world states in language models
• Improving factuality and coherence of language models
• Using language models to understand user preferences

I am funded by an NDSEG Fellowship and Clare Boothe Luce Graduate Fellowship [Press]. Previously, I spent a year at Facebook AI Applied Research, and before that, I obtained my B.S. in Computer Science at the University of Washington, where I worked with Luke Zettlemoyer. You can view more in my CV.

Representative Papers

• QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?
  Belinda Z. Li, Been Kim, Zi Wang
  ArXiv Preprint

• (How) Do Language Models Track State
  Belinda Z. Li, Zifan Carl Guo, Jacob Andreas
  ArXiv Preprint

• Bayesian Preference Elicitation with Language Models
  Kunal Handa, Yarin Gal, Ellie Pavlick, Noah Goodman, Jacob Andreas, Alex Tamkin, Belinda Z. Li
  ArXiv Preprint

• Eliciting Human Preferences with Language Models
  Belinda Z. Li, Alex Tamkin, Noah Goodman, Jacob Andreas
  ICLR, 2025

• Implicit Representations of Meaning in Neural Language Models
  Belinda Z. Li, Maxwell Nye, Jacob Andreas
  ACL, 2021.

All Papers

This list is updated very intermittently. For the latest, up-to-date list, please check my Google Scholar.

• Preference-Conditioned Language-Guided Abstraction
  Andi Peng, Andreea Bobu, Belinda Z Li, Theodore R Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L Griffiths, Julie A Shah
  HRI, 2024

• Bayesian Preference Elicitation with Language Models
  Kunal Handa, Yarin Gal, Ellie Pavlick, Noah Goodman, Jacob Andreas, Alex Tamkin*, Belinda Z. Li*
  ArXiv Preprint * = Equal contribution

• Learning with language-guided state abstractions
  Andi Peng, Ilia Sucholutsky*, Belinda Z Li*, Theodore R Sumers, Thomas L Griffiths, Jacob Andreas, Julie A Shah
  ICLR, 2024 * = Equal contribution

• Eliciting Human Preferences with Language Models
  Belinda Z. Li*, Alex Tamkin*, Noah Goodman, Jacob Andreas
  ArXiv Preprint * = Equal contribution

• Measuring and Manipulating Knowledge Representations in Language Models
  Evan Hernandez, Belinda Z. Li, Jacob Andreas
  ArXiv Preprint

• LaMPP: Language Models as Probabilistic Priors for Perception and Action
  Belinda Z. Li, William Chen, Pratyusha Sharma, Jacob Andreas
  ArXiv Preprint

• Toward Interactive Dictation
  Belinda Z Li, Jason Eisner, Adam Pauls, Sam Thomson
  ACL, 2023

• Language Modeling with Latent Situations
  Belinda Z. Li, Maxwell Nye, Jacob Andreas
  ACL Findings, 2023

• Quantifying Adaptability in Pre-trained Language Models with 500 Tasks
  Belinda Z. Li, Jane Yu, Madian Khabsa, Luke Zettlemoyer, Alon Halevy, Jacob Andreas
  NAACL, 2022

• Implicit Representations of Meaning in Neural Language Models
  Belinda Z. Li, Maxwell Nye, Jacob Andreas
  ACL, 2021.

• On Unifying Misinformation Detection
  Nayeon Lee, Belinda Z. Li, Sinong Wang, Pascale Fung, Hao Ma, Wen-tau Yih, and Madian Khabsa
  NAACL, 2021

• On the Influence of Masking Policies in Intermediate Pre-training
  Qinyuan Ye, Belinda Z. Li, Sinong Wang, Benjamin Bolte, Hao Ma, Wen-tau Yih, Xiang Ren, and Madian Khabsa
  EMNLP, 2021

• Studying Strategically: Learning to Mask for Closed-book QA
  Qinyuan Ye, Belinda Z. Li, Sinong Wang, Benjamin Bolte, Hao Ma, Wen-tau Yih, Xiang Ren, and Madian Khabsa
  ArXiv Preprint

• Efficient One-Pass End-to-End Entity Linking for Questions
  Belinda Z. Li, Sewon Min, Srinivasan Iyer, Yashar Mehdad, and Wen-tau Yih
  EMNLP, 2020

• Linformer: Self-Attention with Linear Complexity
  Sinong Wang, Belinda Z. Li, Madian Khabsa, Han Fang, and Hao Ma
  ArXiv Preprint

• Language Models as Fact Checkers?
  Nayeon Lee, Belinda Z. Li, Sinong Wang, Wen-tau Yih, Hao Ma, and Madian Khabsa
  FEVER (Fact Extraction and VERification) Workshop @ ACL, 2020

• Active Learning for Coreference Resolution using Discrete Annotation
  Belinda Z. Li, Gabriel Stanovsky, and Luke Zettlemoyer
  ACL, 2020

Misc

Outside of work…

• I organize with the MIT Graduate Student Union. We’re fighting for a contract with decent wages, benefits, real recourse, equity for international workers, and more. Please join us!
• I also dance ballet and have recently started (indoor) bouldering.

Fun facts:

• Noam Chomsky is my great(x3)-grand-advisor. Belinda Li → Jacob Andreas → Dan Klein → Chris Manning → Joan Bresnan → Noam Chomsky
• Under very generous definitions, my Erdős–Bacon number is 7. I eagerly welcome any collaborators – academic or entertainment – willing to lower that number. If we loosen the definition of “Bacon number” to allow for video appearances, my Bacon number is 3 through appearing in a video with Bernie Sanders, who happens to have a Bacon number of 2. My Erdős number is 4 through several different paths. However, if we take the standard definition (for those of you Bacon number purists out there), my Bacon number is unfortunately undefined as I have not appeared in a movie.