Verbalised evaluation awareness in language models has little effect on their behaviour

·LessWrong··

TL;DR: We provide evidence that the presence of verbalised evaluation awareness (VEA) in CoTs does not imply eval gaming. We tested this across 8 open-weight LRMs and 4 benchmarks (safety, alignment, moral dilemmas, political opinion) by comparing answer distributions on the same prompts, with and without VEA in the CoT. We find that overall distribution shifts are negligible to small across all benchmarks and experiments, challenging the common assumption that evaluation awareness equals (safet...

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