Jane Dwivedi-Yu

RESEARCH SCIENTIST | NEW YORK CITY, UNITED STATES

Jane Dwivedi-Yu is a researcher at Meta AI. Her current research focuses on improving reasoning and tool usage capabilities of large language models, and evaluating representation harms and notions of morality and norms internalized by these models. Before joining Meta, she completed her PhD in Computer Science at University of California, Berkeley and Bachelors at Cornell University.

Twitter

Google Scholar

Research Areas

Conversational AI

Core Machine Learning

Human & Machine Intelligence

Integrity

Natural Language Processing (NLP)

Reinforcement Learning

Jane's Work

Atlas: Few-shot Learning with Retrieval Augmented Language Models

TimelineQA

Edit Eval: The benchmark for text improvements

The CARE Dataset for Affective Response Detection

Jane's Publications

November 06, 2023

CONVERSATIONAL AI

NLP

ROBBIE: Robust Bias Evaluation of Large Generative Language Models

David Esiobu, Ellen Tan, Saghar Hosseini, Megan Ung, Yuchen Zhang, Jude Fernandes, Jane Yu, Eleonora Presani, Adina Williams, Eric Smith

November 06, 2023

Read the Paper

July 06, 2023

HUMAN & MACHINE INTELLIGENCE

REINFORCEMENT LEARNING

Augmented Language Models: a Survey

Gregoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, Thomas Scialom

July 06, 2023

Read the Paper

December 06, 2022

NLP

"That's so cute!": The CARE Dataset for Affective Response Detection

Jane Yu, Alon Halevy

December 06, 2022

Read the Paper

August 24, 2022

PEER: A Collaborative Language Model

Timo Schick, Christoforos Nalmpantis, Edouard Grave, Fabio Petroni, Gautier Izacard, Jane Dwivedi-Yu, Patrick Lewis, Qingfei You, Sebastian Riedel, Zhengbao Jiang