Measuring Subliminal Trait Transfer with Confusion Matrices

·LessWrong··

Subliminal Learning [Cloud et al] demonstrated the transfer of owl preference by performing SFT on lists of numbers generated by a teacher model that was system prompted (or fine tuned) to imbue its outputs with a love of owls.In this work IPropose a methodology for studying subliminal learning that aims to help avoid selection bias and street-light effect pitfalls.Demonstrate a working experimental setup for small pretrained/base-models (PolyPythias). Previous work uses large language models th...

Read full article →

Related Articles

Measuring the sloppiness of code
doppp · Hacker News · 14h ago
Google will buy half the electricity from one of Finland's nuclear power plants
lukaspetersson · Hacker News · 1d ago
HuggingFace: Security.txt
yarapavan · Hacker News · 13h ago
Rune is now open source
ernestrc · Hacker News · 12h ago
The Deathray: A simple way for an untrusted site to freeze a Mac
auberonedu · Hacker News · 1d ago