# Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization

arXiv: https://arxiv.org/abs/2502.13146 · HTML: https://mlsanity.com/paper/2502.13146/

## Key facts

- Cited by 29 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 46 of its 104 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)
- 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 46)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)
- [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024)

## Built on by (most cited first, 29 of 29)

- [MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding](https://mlsanity.com/paper/2503.13964/) (2025)
- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [Can Large Vision Language Models Read Maps Like a Human?](https://mlsanity.com/paper/2503.14607/) (2025)
- [UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving](https://mlsanity.com/paper/2503.24381/) (2025)
- [SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems](https://mlsanity.com/paper/2506.07564/) (2025)
- [DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning](https://mlsanity.com/paper/2503.11892/) (2025)
- [DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning](https://mlsanity.com/paper/2503.06456/) (2025)
- [Aligning Multimodal LLM with Human Preference: A Survey](https://mlsanity.com/paper/2503.14504/) (2025)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding](https://mlsanity.com/paper/2510.23479/) (2025)
- [MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization](https://mlsanity.com/paper/2603.03192/) (2026)
- [Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization](https://mlsanity.com/paper/2509.25717/) (2025)
- [Visual Preference Optimization with Rubric Rewards](https://mlsanity.com/paper/2604.13029/) (2026)
- [Demystifying the Visual Quality Paradox in Multimodal Large Language Models](https://mlsanity.com/paper/2506.15645/) (2025)
- [CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis](https://mlsanity.com/paper/2508.01594/) (2025)
- [RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks](https://mlsanity.com/paper/2510.14968/) (2025)
- [Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery](https://mlsanity.com/paper/2603.29045/) (2026)
- [AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs](https://mlsanity.com/paper/2506.16112/) (2025)
- [Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision](https://mlsanity.com/paper/2512.23426/) (2025)
- [Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization](https://mlsanity.com/paper/2509.06759/) (2025)
- [A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization](https://mlsanity.com/paper/2510.20291/) (2025)
- [LiMT: A Multi-task Liver Image Benchmark Dataset](https://mlsanity.com/paper/2511.19889/) (2025)
- [HII-DPO: Eliminate Hallucination via Accurate Hallucination-Inducing Counterfactual Images](https://mlsanity.com/paper/2602.10425/) (2026)
- [Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation](https://mlsanity.com/paper/2606.07647/) (2026)
- [TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs](https://mlsanity.com/paper/2507.21584/) (2025)
- [Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition](https://mlsanity.com/paper/2602.19385/) (2026)
- [Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts](https://mlsanity.com/paper/2604.18091/) (2026)
- [ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?](https://mlsanity.com/paper/2606.07962/) (2026)
- [How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective](https://mlsanity.com/paper/2609.36557/) (2026)

## Abstract (arXiv)

The emergence of large Vision Language Models (VLMs) has broadened the scope and capabilities of single-modal Large Language Models (LLMs) by integrating visual modalities, thereby unlocking transformative cross-modal applications in a variety of real-world scenarios. Despite their impressive performance, VLMs are prone to significant hallucinations, particularly in the form of cross-modal inconsistencies. Building on the success of Reinforcement Learning from Human Feedback (RLHF) in aligning LLMs, recent advancements have focused on applying direct preference optimization (DPO) on carefully curated datasets to mitigate these issues. Yet, such approaches typically introduce preference signals in a brute-force manner, neglecting the crucial role of visual information in the alignment process. In this paper, we introduce Re-Align, a novel alignment framework that leverages image retrieval to construct a dual-preference dataset, effectively incorporating both textual and visual preference signals. We further introduce rDPO, an extension of the standard direct preference optimization that incorporates an additional visual preference objective during fine-tuning. Our experimental results demonstrate that Re-Align not only mitigates hallucinations more effectively than previous methods but also yields significant performance gains in general visual question-answering (VQA) tasks. Moreover, we show that Re-Align maintains robustness and scalability across a wide range of VLM sizes and architectures. This work represents a significant step forward in aligning multimodal LLMs, paving the way for more reliable and effective cross-modal applications. We release all the code in https://github.com/taco-group/Re-Align.