Reasoning and learning about injected concepts in language models

·LessWrong··

This work was done as a part of SPAR, under the mentorship of Mirko Bronzi and Damiano Fornasiere. TL;DRWe test models' ability to recover information about their activations by injecting steering vectors, and asking the LLMs to verbalize properties of them. We train models with in-context learning and test for three capabilities: Can models identify the region of layers (early, middle, late) of the injection?Can models identify the relative magnitude (low, medium, high) of the injection?Can mod...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 6h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
Harvard researchers find AI coding agents shifted the bottleneck to code review
judahmeek · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 1d ago