SOURCE-LINKED INTELLIGENCE

Online Self-Weighted Fine-Tuning

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence over training queries. Reinforcement learning (RL) based methods adapt update strength using model-generated rollouts, but often require substantially more sampling and can be unstable on hard tasks. We propose \textbf{Online Self-Weighted Fine-Tuning (OSW-FT)}, a simple method that augments SFT with online, trajectory-level weighting. For each query, OSW-FT estimates the model's current success rate using a small number of inference-only roll

Read original source ↗ Open in workspace

recordType

paper

region

Global