Some unconventional ideas for elicitation

• Training models to elicit responses from other models (c.f. "investigator agents")
• Promptbreeder ("evolve a prompt")
  • Table 1 has many relevant baselines
• Multi-agent ICL (e.g. using different models to do reflection, think of strategies, re-prompt the original model)
  • https://arxiv.org/abs/2410.03768  has an example of this (authors call this "ICRL")
• Multi-turn conversation (similar to above, but where user is like a conversation partner instead of an instructor)
  • Mostly inspired by Janus and Pliny the Liberator
  • The three-layer model implies that 'deeper' conversations dodge the safety post-training, which is like a 'safety wrapper' over latent capabilities
• Train a controller where the parameters are activations for SAE features at a given layer.
  • C.f. AutoSteer