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

Anthropic S-1
SiNTEx · Hacker News · 16h ago
Solar power is becoming bigger than nuclear
geox · Hacker News · 14h ago
The Exponential Time Hypothesis Is False [pdf]
vok · Hacker News · 7h ago
Oldest GUI application that still runs on Windows 11
enlyth · Hacker News · 11h ago
Type Server Protocol
adamnemecek · Hacker News · 11h ago