Language models (LMs) may lead their users to make suboptimal downstream
decisions when they confidently hallucinate. This issue can be mitigated by
having the LM verbally convey the probability that its claims are correct, but
existing models cannot produce text with calibrated confidence statements.
Through the lens of decision-making, we formalize linguistic calibration for
long-form generations: an LM is linguistically calibrated if its generations
enable its users to make calibrated probabilistic predictions. This definition
enables a training framework where a supervised finetuning step bootstraps an
LM to emit long-form generations with confidence statements such as "I estimate
a 30% chance of..." or "I am certain that...", followed by a reinforcement
learning step which rewards generations that enable a user to provide
calibrated answers to related questions. We linguistically calibrate Llama 2 7B
and find in automated and human evaluations of long-form generations that it is
significantly more calibrated than strong finetuned factuality baselines with
comparable accuracy. These findings generalize under distribution shift on
question-answering and under a significant task shift to person biography
generation. Our results demonstrate that long-form generations may be
calibrated end-to-end by constructing an objective in the space of the
predictions that users make in downstream decision-making.

将语言模型从音频转换到文本，并且生成可校准的长篇文本，以便用户能够在后续决策中作出校准的概率预测。