mmd

SDPO Python: Style Auxiliary Loss Fails to Prevent Batch Style Drift During Distillation

Python MMD kernel methods: fixed gamma=1.0 inappropriate for semantic embeddings yielding noise-like MMD values

Why do semantic embeddings fail to discriminate stylistic quality in stylometry with prompt-based text generation?

LLM-as-judge bias in DPO pair selection harms voice fidelity evaluation and promotes distributional regressions