That’s pretty interesting! I would guess that it’s difficult to elicit introspection by default. Most of the papers where this is reported to work well involve fine-tuning the models. So maybe “willingness to self-report honestly” should be something we train models to do.
willingness seems likely to be understating it. a context where the capability is even part of the author context seems like a prereq. finetuning would produce that, with fewshot one has to figure out how to make it correlate. I’ll try some more ideas.
a context where the capability is even part of the author context
Can you unpack that a bit? I’m not sure what you’re pointing to. Maybe something like: few-shot examples of correct introspection (assuming you can identify those)?
That’s pretty interesting! I would guess that it’s difficult to elicit introspection by default. Most of the papers where this is reported to work well involve fine-tuning the models. So maybe “willingness to self-report honestly” should be something we train models to do.
willingness seems likely to be understating it. a context where the capability is even part of the author context seems like a prereq. finetuning would produce that, with fewshot one has to figure out how to make it correlate. I’ll try some more ideas.
Can you unpack that a bit? I’m not sure what you’re pointing to. Maybe something like: few-shot examples of correct introspection (assuming you can identify those)?