# Understanding Alignment in Multimodal LLMs: A Comprehensive Study

arXiv: https://arxiv.org/abs/2407.02477 · HTML: https://mlsanity.com/paper/2407.02477/

## Key facts

- Cited by 23 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 32 of its 42 references that are in the map.
- First posted on arXiv 2 Jul 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 32)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [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)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding](https://mlsanity.com/paper/2306.17107/) (2023)
- [Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study](https://mlsanity.com/paper/2404.10719/) (2024)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)
- [MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training](https://mlsanity.com/paper/2403.09611/) (2024)
- [Generalized Preference Optimization: A Unified Approach to Offline Alignment](https://mlsanity.com/paper/2402.05749/) (2024)
- [Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges](https://mlsanity.com/paper/2311.03287/) (2023)
- [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)
- [Understanding the performance gap between online and offline alignment algorithms](https://mlsanity.com/paper/2405.08448/) (2024)
- [DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback](https://mlsanity.com/paper/2311.10081/) (2023)

## Built on by (most cited first, 23 of 23)

- [Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback](https://mlsanity.com/paper/2412.15838/) (2024)
- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization](https://mlsanity.com/paper/2502.13146/) (2025)
- [Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning](https://mlsanity.com/paper/2503.07906/) (2025)
- [Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey](https://mlsanity.com/paper/2409.11564/) (2024)
- [Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution](https://mlsanity.com/paper/2412.15650/) (2024)
- [Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach](https://mlsanity.com/paper/2411.17760/) (2024)
- [PerPO: Perceptual Preference Optimization via Discriminative Rewarding](https://mlsanity.com/paper/2502.04371/) (2025)
- [Multi-speaker Attention Alignment for Multimodal Social Interaction](https://mlsanity.com/paper/2511.17952/) (2025)
- [Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining](https://mlsanity.com/paper/2506.08022/) (2025)
- [Self-Improvement in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2510.02665/) (2025)
- [Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation](https://mlsanity.com/paper/2512.16201/) (2025)
- [Measuring Agreeableness Bias in Multimodal Models](https://mlsanity.com/paper/2408.09111/) (2024)
- [The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models](https://mlsanity.com/paper/2503.03122/) (2025)
- [OViP: Online Vision-Language Preference Learning for VLM Hallucination](https://mlsanity.com/paper/2505.15963/) (2025)
- [Controlling Multimodal LLMs via Reward-guided Decoding](https://mlsanity.com/paper/2508.11616/) (2025)
- [Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal](https://mlsanity.com/paper/2412.11196/) (2024)
- [STORM: End-to-End Referring Multi-Object Tracking in Videos](https://mlsanity.com/paper/2604.10527/) (2026)
- [Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs](https://mlsanity.com/paper/2604.24395/) (2026)
- [Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs](https://mlsanity.com/paper/2606.09038/) (2026)
- [Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs](https://mlsanity.com/paper/2607.13712/) (2026)
- [Toward a Theory of Value in AI Alignment](https://mlsanity.com/paper/2608.10327/) (2026)
- [PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment](https://mlsanity.com/paper/2608.19598/) (2026)

## Abstract (arXiv)

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models, MLLMs for image understanding tasks encounter challenges like hallucination. In MLLMs, hallucination can occur not only by stating incorrect facts but also by producing responses that are inconsistent with the image content. A primary objective of alignment for MLLMs is to encourage these models to align responses more closely with image information. Recently, multiple works have introduced preference datasets for MLLMs and examined different alignment methods, including Direct Preference Optimization (DPO) and Proximal Policy Optimization (PPO). However, due to variations in datasets, base model types, and alignment methods, it remains unclear which specific elements contribute most significantly to the reported improvements in these works. In this paper, we independently analyze each aspect of preference alignment in MLLMs. We start by categorizing the alignment algorithms into two groups, offline (such as DPO), and online (such as online-DPO), and show that combining offline and online methods can improve the performance of the model in certain scenarios. We review a variety of published multimodal preference datasets and discuss how the details of their construction impact model performance. Based on these insights, we introduce a novel way of creating multimodal preference data called Bias-Driven Hallucination Sampling (BDHS) that needs neither additional annotation nor external models, and show that it can achieve competitive performance to previously published alignment work for multimodal models across a range of benchmarks.