Does self-evaluation enable wireheading in language models?
Formalises and tests wireheading incentives when LLMs' self-grades set their rewards; coupled self-grading inflates grades without accuracy gains, and decoupling mitigates this.
Research
UK AI Security Institute
The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
Focus All
Topic Theory + Alignment
Source UK AISI · 1
Date Any time
1 item