Their method, Direct Preference Optimisation (DPO), relies on a satisfying mathematical trick.

他们的方法，直接偏好优化（DPO），依赖于令人满意的数学技巧。

Over the decades, these ad hoc international forces became more fully established, especially after 1992, when the United Nations Department of Peacekeeping Operations, DPO, was set up.

几十年来， 这些临时国际部队逐渐发展，别是在1992年联合国维持和平行动部（DPO）成立之，它们变得更加制度化。

And I see them on first team all defense, but I think DPO Y should go to yours truly.

我看到他们入选了守阵容一阵，但我认为年度守球员应该归我本人所有。

According to the authors, removing the middleman makes DPO between three and six times more efficient than RLHF, and capable of better performance at tasks such as text summarisation.

据作者称， 消除中间人使得 DPO 的效率比 RLHF 提高三到六倍，并且能够在文本摘要等任务上表现得更好。

But as of March 12th eight out of the ten highest-ranked LLMs on an industry leaderboard used DPO.

但截至 3 月 12 日，行业排行榜上排名高的十个法学硕士中有八个使用了 DPO。