PriFT: Prior-Support Guided Supervised Fine-Tuning

• URL: http://arxiv.org/abs/2606.09396v1
• Date: Mon, 08 Jun 2026 12:14:06 GMT
• Title: PriFT: Prior-Support Guided Supervised Fine-Tuning
• Abstract summary: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation.<n>SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution.<n>We propose PriFT, which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning.
• Score: 74.65198014829393
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models [52.11240605311707]
  Supervised fine-tuning followed by reinforcement learning has become a standard post-training paradigm for large language models.<n>We propose EKSFT (Entropy-KL Selective Fine-Tuning), which selectively masks tokens that exhibit either high entropy or high KL divergence from a reference model.<n> Empirical evaluations on mathematical reasoning benchmarks demonstrate that EKSFT consistently outperforms standard SFT.
  arXiv  Detail & Related papers  (2026-05-28T03:36:05Z)
• Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation [21.687249397347017]
  We propose the Evidential Transformation Network (ETN), a lightweight post-hoc module that converts a pretrained predictor into an evidential model.<n>ETN consistently improves uncertainty estimation over post-hoc baselines while preserving accuracy and adding only minimal computational overhead.
  arXiv  Detail & Related papers  (2026-04-09T16:09:47Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Distributionally Robust Post-hoc Classifiers under Prior Shifts [31.237674771958165]
  We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors. We present an extremely lightweight post-hoc approach that performs scaling adjustments to predictions from a pre-trained model.
  arXiv  Detail & Related papers  (2023-09-16T00:54:57Z)
• Progressive Feature Adjustment for Semi-supervised Learning from Pretrained Models [39.42802115580677]
  Semi-supervised learning (SSL) can leverage both labeled and unlabeled data to build a predictive model. Recent literature suggests that naively applying state-of-the-art SSL with a pretrained model fails to unleash the full potential of training data. We propose to use pseudo-labels from the unlabelled data to update the feature extractor that is less sensitive to incorrect labels.
  arXiv  Detail & Related papers  (2023-09-09T01:57:14Z)
• DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration [38.4461170690033]
  We propose a novel fine-tuning framework, namely distribution regularization with semantic calibration (DR-Tune) DR-Tune employs distribution regularization by enforcing the downstream task head to decrease its classification error on the pretrained feature distribution. To alleviate the interference by semantic drift, we develop the semantic calibration (SC) module.
  arXiv  Detail & Related papers  (2023-08-23T10:59:20Z)
• Debiased Fine-Tuning for Vision-language Models by Prompt Regularization [56.48290708901531]
  We present a new paradigm for fine-tuning large-scale vision pre-trained models on downstream task, dubbed Prompt Regularization (ProReg)<n>ProReg uses the prediction by prompting the pretrained model to regularize the fine-tuning.<n>We show the consistently strong performance of ProReg compared with conventional fine-tuning, zero-shot prompt, prompt tuning, and other state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-01-29T11:53:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.