Papers by Nicholas Carlini

1 papers
Deduplicating Training Data Makes Language Models Better (2022.acl-long)

Copied to clipboard

Challenge: Existing language modeling datasets contain near-duplicate examples and long repetitive substrings.
Approach: They develop tools that allow us to deduplicate existing language modeling datasets . they found that over 1% of the unprompted output of language models is copied verbatim .
Outcome: The proposed tools reduce train-test overlap, which affects over 4% of validation sets, and improve model accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations