Hi, I'm Jane Yu!

I am a researcher in FAIR at Meta working on improving reasoning capabilities of large language models. Before that, I was a Ph.D. student in the EECS department at the University of California, Berkeley.



Education

UC Berkeley

I completed my Ph.D. in 2019 on computational tools for immune repertoire characterization and primer set design and was advised by Professor Yun S. Song. [thesis]

Cornell

I received my Bachelor of Arts and Sciences in both Computer Science and Chemistry in 2014.

Selected Publications

  • Toolformer: Language Models Can Teach Themselves to Use Tools
    Timo Schick, Jane Dwivedi-Yu, Roberta Raileanu, Roberto Dessi, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom
    Neural Information Processing Systems (NeurIPS), 2023 [Oral Presentation]
    [paper] [bibtex]
  • ROBBIE: Robust Bias Evaluation of Large Generative Language Models
    David Esiobu, Xiaoqing Tan, Saghar Hosseini, Megan Ung, Yuchen Zhang, Jude Fernandes, Jane Dwivedi-Yu, Eleonora Presani, Adina Williams, Eric Michael Smith
    Empirical Methods in Natural Language Processing (EMNLP), 2023
    [paper]
  • Active Retrieval Augmented Generation
    Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig
    Empirical Methods in Natural Language Processing (EMNLP), 2023
    [paper] [bibtex]
  • Active Learning Principles for In-Context Learning with Large Language Models
    Katerina Margatina, Timo Schick, Nikolaos Aletras, Jane Dwivedi-Yu
    Findings of the Empirical Methods in Natural Language Processing (EMNLP), 2023
    [paper] [bibtex]
  • Augmented Language Models: a Survey
    Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, Thomas Scialom
    Transactions on Machine Learning Research (TMLR), 2023
    [paper] [bibtex]
  • Atlas: Few-shot Learning with Retrieval Augmented Language Models
    Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, Edouard Grave
    Journal of Machine Learning Research (JMLR), 2023
    [paper] [bibtex]
  • NormBank: A Knowledge Bank of Situational Social Norms
    Caleb Ziems, Jane Dwivedi-Yu, Yi-Chia Wang, Alon Halevy, Diyi Yang
    Association of Computational Linguistics (ACL), 2023
    [paper] [bibtex]
  • TimelineQA: A Benchmark for Question Answering over Timelines
    Wang-Chiew Tan, Jane Dwivedi-Yu, Yuliang Li, Lambert Mathias, Marzieh Saeidi, Nathan Yan, Alon Halevy
    Findings of the Association of Computational Linguistics (ACL), 2023
    [paper] [bibtex] [code]
  • Learnings from Data Integration for Augmented Language Models
    Alon Halevy, Jane Dwivedi-Yu
    [paper] [bibtex]
  • Improving Wikipedia Verifiability with AI
    Fabio Petroni, Samuel Broscheit, Aleksandra Piktus, Patrick Lewis, Gautier Izacard, Jane Dwivedi-Yu, Maria Lomeli, Timo Schick, Pierre-Emmanuel Mazaré, Armand Joulin, Edouard Grave, Sebastian Riedel
    Nature Machine Intelligence, 2023
    [paper] [bibtex] [code]
  • Using Comments for Predicting the Affective Response to Social Media Posts
    Yi-Chia Wang*, Jane Dwivedi-Yu*, Alon Halevy, Robert E. Kraut
    International Conference on Affective Computing and Intelligent Interaction (ACII), 2023
  • Consequences of Conflicts in Online Conversations
    Shirley Hayati, Kristen Altenburger, Jane Dwivedi-Yu Robert E. Kraut, Yi-Chia Wang
    Under Review
    International AAAI Conference on Web and Social Media (ICWSM), 2024
  • Selective whole-genome amplification reveals population genetics of Leishmania braziliensis directly from patient skin biopsies
    Olivia A. Pilling, Cooper A. Grace, Joao L. Reis-Cunha, Alexander SF Berry, Matthew W. Mitchell, Jane A. Yu, Clara Malekshahi, Elise Krespan, Christina K. Go, Claudia Lombana, Yun S Song, Camila F Amorim, Alexsandro S. Lago, Lucas P. Carvalho, Edgar M. Carvalho, Dustin Brisson, Phillip Scott, Daniel C. Jeffares, Daniel P. Beiting
    PLOS Pathogens, 2023
    [paper] [bibtex]
  • A fast machine-learning-guided primer design pipeline for selective whole genome amplification
    Jane Dwivedi-Yu, Zachary Oppler, Matthew Mitchell, Yun S. Song, Dustin Brisson
    PLOS Computational Biology, 2023
    [paper] [bibtex] [code]
  • EditEval: An Instruction-Based Benchmark for Text Improvements
    Jane Dwivedi-Yu, Timo Schick, Zhengbao Jiang, Maria Lomeli, Patrick Lewis, Gautier Izacard, Edouard Grave, Sebastian Riedel, Fabio Petroni
    [paper] [bibtex] [code] [leaderboard]
  • PEER: A Collaborative Language Model
    Timo Schick, Jane Dwivedi-Yu, Zhengbao Jiang, Fabio Petroni, Patrick Lewis, Gautier Izacard, Qingfei You, Christoforos Nalmpantis, Edouard Grave, Sebastian Riedel
    International Conference on Learning Representations (ICLR), 2023
    [paper] [bibtex]
  • “That’s so cute!”: The CARE Dataset for Affective Response Detection
    Jane Dwivedi-Yu, Alon Halevy
    Computational Natural Language Learning (CoNLL), 2022
    [paper] [bibtex] [code]
  • Affective Signals in a Social Media Recommender System
    Jane Dwivedi-Yu, Yi-Chia Wang, Lijing Qin, Cristian Canton Ferrer, Alon Halevy
    Knowledge Discovery and Data Mining (KDD), 2022
    [paper] [bibtex] || [presentation] [poster]
  • Quantifying Adaptability in Pre-trained Language Models with 500 Tasks
    Belinda Li, Jane A. Yu, Madian Khabsa, Alon Halevy, Luke Zettlemoyer, Jacob Andreas
    North American Chapter of the Association for Computational Linguistics (NAACL), 2022
    [paper] [bibtex] [code]
  • The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems
    Caleb Ziems, Jane A. Yu, Yi-Chia Wang, Alon Halevy, Diyi Yang
    Association of Computational Linguistics (ACL), 2022
    [paper] [bibtex] [code]
  • Understanding Conflicts in Online Conversations
    Sharon Levy, Robert E. Kraut, Jane A. Yu, Kristen Altenburger, Yi-Chia Wang
    International World Wide Web Conference (WWW), 2022
    [paper] [bibtex]
  • Detecting Inspiring Content on Social Media
    Oana Ignat, Y-Lan Boureau, Jane A. Yu, Alon Halevy
    International Conference on Affective Computing and Intelligent Interaction (ACII), 2021
    [paper] [bibtex] [code]
  • Worldwide genetic variation of the IGHV and TRBV immune receptor gene families in humans
    Shishi Luo*, Jane A. Yu*, Heng Li, and Yun S. Song
    Life Science Alliance, 2019
    [paper] [bibtex] [code]
  • Estimating copy number and allelic variation at the immunoglobulin heavy chain locus using short reads
    Shishi Luo, Jane A. Yu, Heng Li, and Yun S. Song
    PLoS Comput Biol, 2016
    [paper] [bibtex]

Previous Research Interns

Dheeraj Mekala (Summer 2023)
Alex Havrilla (Summer 2023)
Carlos Gemmell (Summer 2023)
Kexun Zhang (Summer 2023)
Seraphina Goldfarb-Tarrant (Fall 2022)
Katerina Margatina (Fall 2022)
Zhengbao Jiang (Summer 2022)
Caleb Ziems (Summer 2021 and Summer 2022)
Jing Nathan Yan (Summer 2022)
Shirley Hayati (Summer 2022)
Sharon Levy (Summer 2021)
Belinda Li (Summer 2021)
Candace Ross (Fall 2020)
Oana Ignat (Summer 2020)