Post-Training on Chen Kai Bloghttps://www.chenk.top/en/tags/post-training/Recent content in Post-Training on Chen Kai BlogHugoenMon, 30 Mar 2026 09:00:00 +0000LLM Engineering (4): Post-training — SFT, DPO, RLHF, RLAIFhttps://www.chenk.top/en/llm-engineering/04-post-training/Mon, 30 Mar 2026 09:00:00 +0000https://www.chenk.top/en/llm-engineering/04-post-training/<p>A base model from pretraining can complete text but cannot follow instructions, refuse harmful requests, or maintain a persona—these are post-training behaviors. Post-training is where the gap between a research paper&rsquo;s claims and a production-grade model lies. This chapter covers what each post-training algorithm optimizes, why most reward models are subtly flawed, and the effective methods for 2026.</p> <p><figure class="article-figure"> <img src="https://blog-pic-ck.oss-cn-beijing.aliyuncs.com/posts/en/llm-engineering/04-post-training/illustration_1.png" alt="LLM Engineering (4): Post-training — SFT, DPO, RLHF, RLAIF — Chapter overview" loading="lazy" decoding="async" class="content-image"> </figure> </p>