# MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning

arXiv: https://arxiv.org/abs/2506.15706 · HTML: https://mlsanity.com/paper/2506.15706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Orca-Math: Unlocking the potential of SLMs in Grade School Math](https://mlsanity.com/paper/2402.14830/) (2024)
- [MathScale: Scaling Instruction Tuning for Mathematical Reasoning](https://mlsanity.com/paper/2403.02884/) (2024)
- [OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset](https://mlsanity.com/paper/2402.10176/) (2024)
- [MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs](https://mlsanity.com/paper/2402.16352/) (2024)
- [MathPile: A Billion-Token-Scale Pretraining Corpus for Math](https://mlsanity.com/paper/2312.17120/) (2023)

## Abstract (arXiv)

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) as it requires ensuring the correctness of each reasoning step. Researchers have been strengthening the mathematical reasoning abilities of LLMs through supervised fine-tuning, but due to the inability to suppress incorrect outputs, illusions can easily arise. Recently, Direct Preference Optimization (DPO) has been widely adopted for aligning human intent by using preference data to prevent LLMs from generating incorrect outputs. However, it has shown limited benefits in long-chain mathematical reasoning, mainly because DPO struggles to effectively capture the differences between accepted and rejected answers from preferences in long-chain data. The inconsistency between DPO training and LLMs' generation metrics also affects the effectiveness of suppressing incorrect outputs. We propose the Multi-Granularity Direct Preference Optimization (MDPO) method, optimizing the mathematical reasoning of LLMs at three granularities: Solution2Solution, Inference2Inference, and Step2Step. Solution2Solution focuses on the correctness of entire long-chain reasoning; Inference2Inference concentrates on logical reasoning between steps; Step2Step corrects computational errors in steps, enhancing the computational capabilities of LLMs. Additionally, we unify the training objectives of the three granularities to align with the generation metrics. We conducted experiments on the open-source models Qwen2 and Llama3, achieving improvements of 1.7% and 0.9% on the GSM8K dataset, and 2.3% and 1.2% on the MATH dataset, outperforming DPO and other DPO variant methods. Furthermore, we also provide a pipeline for constructing MDPO training data that is simple and does not require manual annotation costs.