Alignment Forum August 10, 2026 · Communities

Four LLM loss functions → four flavors of LLM misalignment

It seems to me that, for every loss function that we use to train LLMs, we get a very distinct flavor of LLM misalignment. Here’s the summary table, and then we’ll go through the rows separately.Training stageLoss functionFlavor of misalignment[1]Famous examplesPretraining & SFTImitative learning (next-token prediction