voidism/DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

↗ Open on GitHub

Stars

558

Forks

68

Language

Python

License

—

Last push

2 months ago

Python large-language-models factuality hallucinations

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.