Jason Wei
AI researcher known for chain-of-thought prompting, instruction tuning, and emergent abilities of LLMs; previously at OpenAI and Google Brain.
- Role
- research-scientist
- Currently at
- Meta Superintelligence Labs
- twitter.com/_jasonwei
- GitHub
- github.com/jasonwei20
- Scholar
- scholar.google.com/citations
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
preprint
GPT-4 Technical Report
gpt-4-technical-report
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
arXiv 2023
FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
arXiv 2023
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
ACL
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
The MultiBERTs: BERT Reproductions for Robustness Analysis
the-multiberts-bert-reproductions-for-1
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
eda-easy-data-augmentation-techniques-for-1
Eval contributions
2Affiliations
Frequent co-authors
10from 8 papers
Hyung Won Chung
researcher
Barret Zoph
founder
Denny Zhou
researcher
Alethea Power
researcher
Angela Jiang
Daniel Levy
David Dohan
researcher
Derek Chen
Ellie Pavlick
Giambattista Parascandolo