Together AI 平台支持 DPO：技术深度解析

AI 摘要

Together AI 宣布其微调平台现已支持直接偏好优化（DPO），这是一种无需强化学习即可将语言模型与人类偏好对齐的技术。文章详细介绍了 DPO 的原理、与 RLHF 的对比，并推荐先进行监督微调（SFT）再进行 DPO 的两阶段训练方法，以提升模型的有用性、真实性和无害性。

正文节选

We're excited to announce that the Together Fine-Tuning Platform now supports Direct Preference Optimization (DPO)! This technique allows developers to align language models with human preferences creating more helpful, accurate, and tailored AI assistants. In this deep-dive blogpost, we provide details of what DPO is, how it works, when to use it and code examples. If you'd like to jump straight into code have a look at our code notebook. Tuning LLMs on Preference Data Modern language model dev

发布时间：—

抓取时间：2026-08-03 01:13

来源机构：Together AI