Megadose AI progress, ranked and analyzed.

Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs

· ArXiv · AI/CL/LG ·
Small proxy runs may be enough to set the SFT-versus-RL data split for larger models.

The paper frames annotation budgeting as a near-optimal region rather than a single best ratio. It reports that those regions stay broad even within 2-10% of peak performance, widen with model scale, and transfer from smaller proxy models to larger targets. The result is meant to reduce exhaustive large-model searches across SFT and RL allocations. The authors say the pattern holds across tasks, model families, and both off-policy preference RL and on-policy reward supervision. ArXiv · AI/CL/LG's note

score 4

Categories: Research