flâneur

Deft Fixing LLM Writing with Distribution Fine-Tuning

deftwriting.com · 4,953 words · saved by 1 readers

Rosmine's research paper on Distribution Fine-Tuning: the measurement stack, SFT failure modes, DFT results, model comparisons, methods, data, and limitations.

Slop. It's not just annoying — it's exhausting. You're absolutely right to be annoyed by it, and in this blog I will delve into a solution. You've probably noticed most models have their favorite words or phrases they overuse, like "—", "it's not X, it's Y", or "delve". Before investigating the solution, I first address the metrics I use to measure output quality. Instead of measuring "quality" itself, which is not well defined, I measure similarity to human writing samples. Metrics N-Gram Token Distribution L2 Distance This metric captures word choice similarity, and is useful for…

saved by

related reading