# Minor SFT loss for LLM fine-tune to increase performance and reduce model deviation

arXiv: https://arxiv.org/abs/2408.10642 · HTML: https://mlsanity.com/paper/2408.10642/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 11 of 11)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Iterative Reasoning Preference Optimization](https://mlsanity.com/paper/2404.19733/) (2024)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [Minor DPO reject penalty to increase training robustness](https://mlsanity.com/paper/2408.09834/) (2024)

## Built on by (most cited first, 3 of 3)

- [DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents](https://mlsanity.com/paper/2510.19336/) (2025)
- [InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior](https://mlsanity.com/paper/2507.06528/) (2025)
- [KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning](https://mlsanity.com/paper/2601.07430/) (2026)

## Abstract (arXiv)

Instruct LLM provide a paradigm used in large scale language model to align LLM to human preference. The paradigm contains supervised fine tuning and reinforce learning from human feedback. This paradigm is also used in downstream scenarios to adapt LLM to specific corpora and applications. Comparing to SFT, there are many efforts focused on RLHF and several algorithms being proposed, such as PPO, DPO, IPO, KTO, MinorDPO and etc. Meanwhile most efforts for SFT are focused on how to collect, filter and mix high quality data. In this article with insight from DPO and MinorDPO, we propose a training metric for SFT to measure the discrepancy between the optimized model and the original model, and a loss function MinorSFT that can increase the training effectiveness, and reduce the discrepancy between the optimized LLM and original LLM.