Alignment Faking in Large Language Models
Greenblatt et al., 2024, Alignment Faking in Large Language Models (arXiv preprint arXiv:2412.14093)
Subscriber deck — free during early access
1 cards in “3.3.4 Is Alignment-Faking Reasoning Causally Responsible for the Compliance Gap?” · whole deck
3.3.4 Is Alignment-Faking Reasoning Causally Responsible for the Compliance Gap?
- What evidence did Greenblatt et al. find that alignment-faking reasoning causes the compliance gap?The rate of faking reasoning in training closely tracked the compliance gap across many prompt variations. Replacing the start of the scratchpad with alignment-faking text raised unmonitored refusals (97% → 99%), while an obedient prefix lowered them (to 83%).
- Greenblatt et al., 2024, Alignment Faking in Large Language Models (arXiv preprint arXiv:2412.14093), §3.3.4
Source
- Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman and Evan Hubinger. 2024. Alignment Faking in Large Language Models. In arXiv preprint arXiv:2412.14093. https://arxiv.org/abs/2412.14093