V
Vincent Zhao
Publications - 14
Citations - 477
Vincent Zhao is an academic researcher. The author has contributed to research in topics: Computer science & Expectation–maximization algorithm. The author has co-authored 3 publications.
Papers
More filters
Journal ArticleDOI
Scaling Instruction-Finetuned Language Models
Hyung Won Chung,Le Hou,Shayne Longpre,Barret Zoph,Yi Tay,William Fedus,Eric Li,Xuezhi Wang,Mostafa Dehghani,Siddhartha Brahma,Albert Webson,Shixiang Gu,Zhuyun Dai,Mirac M. Suzgun,Xinyun Chen,Aakanksha Chowdhery,Dasha Valter,Sharan Narang,Gaurav Mishra,Adams Wei Yu,Vincent Zhao,Yanping Huang,Andrew M. Dai,Hongkun Yu,Slav Petrov,Ed H. Chi,Jeffrey Dean,Jacob Devlin,Adam Roberts,Denny Zhou,Quoc V. Le,Jason Loh Seong Wei +31 more
TL;DR: This result shows that instruction and UL2 continued pre-training are complementary compute-efficient methods to improve the performance of language models without increasing model scale.
Proceedings ArticleDOI
Promptagator: Few-shot Dense Retrieval From 8 Examples
Zhuyun Dai,Vincent Zhao,Ji Ma,Yi Luan,Jianmo Ni,Jingwen Lu,Anton Bakalov,Kelvin Guu,Keith Hall,Ming-Wei Chang +9 more
TL;DR: This paper proposes Promptbase Query Generation for Retriever (PROMPTAGATOR), which leverages large language models (LLM) as a few-shot query generator, and creates task-specific retrievers based on the generated data.
Proceedings Article
Mixture-of-Experts with Expert Choice Routing
Yanqi Zhou,Tao Lei,Han-Chu Liu,Nan Du,Yanping Huang,Vincent Zhao,Andrew M. Dai,Zhifeng Chen,Quoc Le,James Laudon +9 more
TL;DR: A heterogeneous mixture-of-experts employing an expert choice method that outperforms the T5 dense model in 7 out of the 11 tasks and improves training convergence time by more than 2 × .
Proceedings ArticleDOI
Dialog Inpainting: Turning Documents into Dialogs
TL;DR: dial inpainting takes the text of any document and transforms it into a two- person dialog between the writer and an imagined reader, and uses a dialog inpainter to predict what the imagined reader asked or said in between each of the writer's utterances.
Proceedings Article
RARR: Researching and Revising What Language Models Say, Using Language Models
Luyu Gao,Zhuyun Dai,Panupong Pasupat,Anthony Chen,Arun Tejasvi Chaganty,Yicheng Fan,Vincent Zhao,Ni Lao,Hongrae Lee,Da-Cheng Juan,Kelvin Guu +10 more
TL;DR: This paper propose a system that automatically finds attribution for the output of any text generation model and post-edits the output to fix unsupported content while preserving the original output as much as possible.