# InCo-DPO: Balancing Distribution Shift and Data Quality for Enhanced Preference Optimization

arXiv: https://arxiv.org/abs/2503.15880 · HTML: https://mlsanity.com/paper/2503.15880/

## Key facts

- Cited by 4 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 30 of its 40 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Placed in

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

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [HelpSteer2: Open-source dataset for training top-performing reward models](https://mlsanity.com/paper/2406.08673/) (2024)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [Disentangling Length from Quality in Direct Preference Optimization](https://mlsanity.com/paper/2403.19159/) (2024)
- [Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data](https://mlsanity.com/paper/2404.14367/) (2024)
- [Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences](https://mlsanity.com/paper/2404.03715/) (2024)
- [Fast Best-of-N Decoding via Speculative Rejection](https://mlsanity.com/paper/2410.20290/) (2024)
- [Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning](https://mlsanity.com/paper/2402.13669/) (2024)
- [WPO: Enhancing RLHF with Weighted Preference Optimization](https://mlsanity.com/paper/2406.11827/) (2024)
- [From Lists to Emojis: How Format Bias Affects Model Alignment](https://mlsanity.com/paper/2409.11704/) (2024)
- [Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment](https://mlsanity.com/paper/2408.06266/) (2024)
- [Efficient RLHF: Reducing the Memory Usage of PPO](https://mlsanity.com/paper/2309.00754/) (2023)
- [Better Synthetic Data by Retrieving and Transforming Existing Datasets](https://mlsanity.com/paper/2404.14361/) (2024)
- [AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization](https://mlsanity.com/paper/2410.10148/) (2024)
- [Towards a Unified View of Preference Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2409.02795/) (2024)
- [Ada-Instruct: Adapting Instruction Generators for Complex Reasoning](https://mlsanity.com/paper/2310.04484/) (2023)

## Built on by (most cited first, 4 of 4)

- [What Matters in Data for DPO?](https://mlsanity.com/paper/2508.18312/) (2025)
- [Understanding the Impact of Sampling Quality in Direct Preference Optimization](https://mlsanity.com/paper/2506.04272/) (2025)
- [AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection](https://mlsanity.com/paper/2609.05899/) (2026)
- [Anchors Enhance Controllability and Reasoning of Diffusion Language Models](https://mlsanity.com/paper/2610.15097/) (2026)

## Abstract (arXiv)

Direct Preference Optimization (DPO) optimizes language models to align with human preferences. Utilizing on-policy samples, generated directly by the policy model, typically results in better performance due to its distribution consistency with the model compared to off-policy samples. This paper identifies the quality of candidate preference samples as another critical factor. While the quality of on-policy data is inherently constrained by the capabilities of the policy model, off-policy data, which can be derived from diverse sources, offers greater potential for quality despite experiencing distribution shifts. However, current research mostly relies on on-policy data and neglects the value of off-policy data in terms of data quality, due to the challenge posed by distribution shift. In this paper, we propose InCo-DPO, an efficient method for synthesizing preference data by integrating on-policy and off-policy data, allowing dynamic adjustments to balance distribution shifts and data quality, thus finding an optimal trade-off. Consequently, InCo-DPO overcomes the limitations of distribution shifts in off-policy data and the quality constraints of on-policy data. We evaluated InCo-DPO with the Alpaca-Eval 2.0 and Arena-Hard benchmarks. Experimental results demonstrate that our approach not only outperforms both on-policy and off-policy data but also achieves a state-of-the-art win rate of 60.8 on Arena-Hard with the vanilla DPO using Gemma-2 model.