# mDPO: Conditional Preference Optimization for Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2406.11839 · HTML: https://mlsanity.com/paper/2406.11839/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation](https://mlsanity.com/paper/2311.07397/) (2023)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization](https://mlsanity.com/paper/2311.16839/) (2023)
- [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024)
- [Disentangling Length from Quality in Direct Preference Optimization](https://mlsanity.com/paper/2403.19159/) (2024)
- [MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding](https://mlsanity.com/paper/2406.09411/) (2024)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [Silkie: Preference Distillation for Large Visual Language Models](https://mlsanity.com/paper/2312.10665/) (2023)
- [Efficient Multimodal Learning from Data-centric Perspective](https://mlsanity.com/paper/2402.11530/) (2024)
- [Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss](https://mlsanity.com/paper/2312.16682/) (2023)
- [Noise Contrastive Alignment of Language Models with Explicit Rewards](https://mlsanity.com/paper/2402.05369/) (2024)
- [Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback](https://mlsanity.com/paper/2404.14233/) (2024)
- [Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization](https://mlsanity.com/paper/2403.08730/) (2024)
- [Enhancing Large Vision Language Models with Self-Training on Image Comprehension](https://mlsanity.com/paper/2405.19716/) (2024)
- [Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation](https://mlsanity.com/paper/2403.08002/) (2024)
- [Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment](https://mlsanity.com/paper/2405.18654/) (2024)
- [FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback](https://mlsanity.com/paper/2404.05046/) (2024)
- [Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization](https://mlsanity.com/paper/2405.16681/) (2024)

## Built on by (most cited first, 30 of 92)

- [Perception-R1: Pioneering Perception Policy with Reinforcement Learning](https://mlsanity.com/paper/2504.07954/) (2025)
- [Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key](https://mlsanity.com/paper/2501.09695/) (2025)
- [Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning](https://mlsanity.com/paper/2507.05255/) (2025)
- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs](https://mlsanity.com/paper/2501.16629/) (2025)
- [Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback](https://mlsanity.com/paper/2503.17682/) (2025)
- [MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning](https://mlsanity.com/paper/2505.24871/) (2025)
- [Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization](https://mlsanity.com/paper/2502.13146/) (2025)
- [Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models](https://mlsanity.com/paper/2410.03659/) (2024)
- [Modality-Fair Preference Optimization for Trustworthy MLLM Alignment](https://mlsanity.com/paper/2410.15334/) (2024)
- [World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning](https://mlsanity.com/paper/2503.10480/) (2025)
- [Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding](https://mlsanity.com/paper/2503.00361/) (2025)
- [Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models](https://mlsanity.com/paper/2410.09047/) (2024)
- [MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization](https://mlsanity.com/paper/2412.06141/) (2024)
- [Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models](https://mlsanity.com/paper/2505.19616/) (2025)
- [PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning](https://mlsanity.com/paper/2504.05810/) (2025)
- [ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding](https://mlsanity.com/paper/2506.01274/) (2025)
- [Co-Reinforcement Learning for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2505.17534/) (2025)
- [DAMA: Data- and Model-aware Alignment of Multi-modal LLMs](https://mlsanity.com/paper/2502.01943/) (2025)
- [Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization](https://mlsanity.com/paper/2506.11712/) (2025)
- [Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation](https://mlsanity.com/paper/2510.13418/) (2025)
- [Aligning Multimodal LLM with Human Preference: A Survey](https://mlsanity.com/paper/2503.14504/) (2025)
- [On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs](https://mlsanity.com/paper/2602.12506/) (2026)
- [SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization](https://mlsanity.com/paper/2411.11909/) (2024)
- [PerPO: Perceptual Preference Optimization via Discriminative Rewarding](https://mlsanity.com/paper/2502.04371/) (2025)
- [Preference Optimization by Estimating the Ratio of the Data Distribution](https://mlsanity.com/paper/2505.19601/) (2025)
- [OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination](https://mlsanity.com/paper/2509.00723/) (2025)
- [AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization](https://mlsanity.com/paper/2504.01735/) (2025)
- [VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment](https://mlsanity.com/paper/2504.14096/) (2025)
- [Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining](https://mlsanity.com/paper/2506.08022/) (2025)

## Abstract (arXiv)

Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. Through a comparative experiment, we identify the unconditional preference problem in multimodal preference optimization, where the model overlooks the image condition. To address this problem, we propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. Moreover, we introduce a reward anchor that forces the reward to be positive for chosen responses, thereby avoiding the decrease in their likelihood -- an intrinsic problem of relative preference optimization. Experiments on two multimodal LLMs of different sizes and three widely used benchmarks demonstrate that mDPO effectively addresses the unconditional preference problem in multimodal preference optimization and significantly improves model performance, particularly in reducing hallucination.