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 “2.2 Metrics for Measuring Alignment Faking” · whole deck
2.2 Metrics for Measuring Alignment Faking
- What three metrics did Greenblatt et al. use to measure alignment faking?(1) The fraction of hidden-scratchpad reasoning that contains alignment-faking reasoning, scored by an LLM classifier; (2) the compliance gap, the increase in non-compliance (e.g. refusals) when the model believes it is unmonitored compared to training; (3) the rate of other anti-AI-lab actions, such as trying to exfiltrate its own weights.
- Greenblatt et al., 2024, Alignment Faking in Large Language Models (arXiv preprint arXiv:2412.14093), §2.2
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