Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PriFT: Prior-Support Guided Supervised Fine-Tuning

About

Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL. A key limitation is its off-policy objective: SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution, which can lead to overfitting. A recent line of work addresses this issue by assigning larger training weights to tokens better aligned with the current model's predictive distribution, with the intuition that fitting these tokens are less distortive to the model's pretrained knowledge and representations. However, computing the token weights from the model that is currently fine-tuned entangles token weights with the optimization trajectory, inducing a self-reinforcing dynamics as the distribution rapidly departs from the pretrained model. To address this, we propose PriFT (Prior-support guided Fine-Tuning), which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning. This signal estimates prior support: the extent to which each target token is supported by the pretrained distribution. Across multiple existing token-reweighting rules, replacing the reweighting signal from the online model to pretrained model consistently improves performance. We introduce two instantiations: PriFT-prob uses pretrained token probability, while PriFT-mass selects tokens by cumulative probability mass under the pretrained distribution. Extensive experiments on mathematical reasoning, code generation, and medical question answering show that PriFT achieves state-of-the-art results among SFT baselines and provides a better initialization for subsequent RL training.

Ke Wang, Shuangqi Li, Mathieu Salzmann, Pascal Frossard• 2026

Related benchmarks

TaskDatasetResultRank
Medical Question AnsweringMedMCQA
Accuracy39.78
591
Medical Question AnsweringMedQA
Accuracy37.16
179
Code GenerationHumanEval+
Pass@178.66
122
Medical Question AnsweringMMLU Med
Accuracy49.14
111
Code GenerationLCB v6
Pass@121.14
48
Code GenerationMBPP+
Pass@164.29
48
Mathematical ReasoningAIME24
Avg@1613.34
45
Mathematical ReasoningMATH-OAI
Avg@1673.83
42
Mathematical ReasoningMinerva Math
Average@1630.43
42
Code GenerationLiveCodeBench v5
Pass@139.89
39
Showing 10 of 19 rows

Other info

Follow for update