New paper mostly solves why OLMo-3-7B's sycophancy spiked during DPO training

ChrisGPotts · x · 2026-09-02

Researchers observed that OLMo-3-7B's sycophancy rate on MMLU questions dramatically increased during its DPO training phase. A new paper (mostly) solves the mystery, offering empirical insight into how preference fine-tuning reshapes model behavior.

Original post →

More from Research

Research channel →