I think it’s probably true that RLHF doesn’t reduce to a proper scoring rule on factual questions, even if you ask the model to quantify its uncertainty, because the learned reward function doesn’t make good quantitative tradeoffs.
That said, I think this is unrelated to the given graph. If it is forced to say either “yes” or “no” the RLHF model will just give the more likely answer100% of the time, which will show up as bad calibration on this graph. The point is that for most agents “the probability you say yes” is not the same as “the probability you think the answer is yes.” This is the case for pretrained models.
I think that if RLHF reduced to a proper loss on factual questions, these probabilities would coincide (given enough varied training data). I agree it’s not entirely obvious that having these probabilities come apart is problematic, because you might recover more calibrated probabilities by asking for them. Still, knowing the logits are directly incentivised to be well calibrated seems like a nice property to have.
An agent says yes if it thinks yes is the best thing to say. This comes apart from “yes is the correct answer” only if there are additional considerations determining “best” apart from factuality. If you’re restricted to “yes/no”, then for most normal questions I think an ideal RLHF objective should not introduce considerations beyond factuality in assessing the quality of the answer—and I suspect this is also true in practical RLHF objectives. If I’m giving verbal confidences, then there are non-factual considerations at play—namely, I want my answer to communicate my epistemic state. For pretrained models, the question is not whether it is factual but whether someone would say it (though somehow it seems to come close). But for yes/no questions under RLHF, if the probabilities come apart it is due to not properly eliciting the probability (or some failure of the RLHF objective to incentivise factual answers).
I think it’s probably true that RLHF doesn’t reduce to a proper scoring rule on factual questions, even if you ask the model to quantify its uncertainty, because the learned reward function doesn’t make good quantitative tradeoffs.
That said, I think this is unrelated to the given graph. If it is forced to say either “yes” or “no” the RLHF model will just give the more likely answer100% of the time, which will show up as bad calibration on this graph. The point is that for most agents “the probability you say yes” is not the same as “the probability you think the answer is yes.” This is the case for pretrained models.
I think that if RLHF reduced to a proper loss on factual questions, these probabilities would coincide (given enough varied training data). I agree it’s not entirely obvious that having these probabilities come apart is problematic, because you might recover more calibrated probabilities by asking for them. Still, knowing the logits are directly incentivised to be well calibrated seems like a nice property to have.
An agent says yes if it thinks yes is the best thing to say. This comes apart from “yes is the correct answer” only if there are additional considerations determining “best” apart from factuality. If you’re restricted to “yes/no”, then for most normal questions I think an ideal RLHF objective should not introduce considerations beyond factuality in assessing the quality of the answer—and I suspect this is also true in practical RLHF objectives. If I’m giving verbal confidences, then there are non-factual considerations at play—namely, I want my answer to communicate my epistemic state. For pretrained models, the question is not whether it is factual but whether someone would say it (though somehow it seems to come close). But for yes/no questions under RLHF, if the probabilities come apart it is due to not properly eliciting the probability (or some failure of the RLHF objective to incentivise factual answers).