# A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

arXiv: https://arxiv.org/abs/2606.11189 · HTML: https://mlsanity.com/paper/2606.11189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [RL's Razor: Why Online Reinforcement Learning Forgets Less](https://mlsanity.com/paper/2509.04259/) (2025)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification](https://mlsanity.com/paper/2508.05629/) (2025)
- [Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions](https://mlsanity.com/paper/2402.18060/) (2024)
- [Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning](https://mlsanity.com/paper/2402.13669/) (2024)
- [Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting](https://mlsanity.com/paper/2510.18874/) (2025)
- [A Survey on Data Selection for LLM Instruction Tuning](https://mlsanity.com/paper/2402.05123/) (2024)
- [Preserving Diversity in Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2408.16673/) (2024)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models](https://mlsanity.com/paper/2504.00869/) (2025)
- [Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)](https://mlsanity.com/paper/2507.12856/) (2025)
- [Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning](https://mlsanity.com/paper/2510.10974/) (2025)
- [Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum](https://mlsanity.com/paper/2510.00526/) (2025)
- [ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection](https://mlsanity.com/paper/2601.09195/) (2026)
- [Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting](https://mlsanity.com/paper/2601.02151/) (2026)
- [Calibrated Language Models and How to Find Them with Label Smoothing](https://mlsanity.com/paper/2508.00264/) (2025)

## Abstract (arXiv)

Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with the model prior. Strictly fitting toward this one-hot target may be suboptimal, especially when the pretrained model encodes a rich knowledge prior. In this work, we reinterpret SFT as target distribution design: instead of studying only the loss objective, we analyze the token-level target that the loss drives the model to match. We introduce the Q-target framework, which decomposes SFT supervision into two explicit choices: (1) how strongly to rely on the observed token, and (2) how to allocate the remaining probability mass over alternatives. This perspective unifies many existing SFT variants as implicit choices of the target distribution Q. Building on this view, we propose Target-SFT which constructs the training objective directly from the desired target distribution. This method consistently outperforms across the ten reasoning dataset-model settings evaluated, showing the effectiveness of this target-based approach. Overall, our formulation reveals a more fundamental design principle for SFT training and opens a broader search space for SFT objectives.