# VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment

arXiv: https://arxiv.org/abs/2410.09421 · HTML: https://mlsanity.com/paper/2410.09421/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 33 of its 55 references that are in the map.
- First posted on arXiv 12 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- 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 33)

- [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)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding](https://mlsanity.com/paper/2306.17107/) (2023)
- [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)
- [MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning](https://mlsanity.com/paper/2309.07915/) (2023)
- [SVIT: Scaling up Visual Instruction Tuning](https://mlsanity.com/paper/2307.04087/) (2023)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback](https://mlsanity.com/paper/2311.10081/) (2023)
- [MileBench: Benchmarking MLLMs in Long Context](https://mlsanity.com/paper/2404.18532/) (2024)
- [Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback](https://mlsanity.com/paper/2404.14233/) (2024)
- [Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.05199/) (2023)
- [VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models](https://mlsanity.com/paper/2311.17404/) (2023)
- [Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond](https://mlsanity.com/paper/2310.02071/) (2023)

## Built on by (most cited first, 30 of 58)

- [VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models](https://mlsanity.com/paper/2411.17451/) (2024)
- [InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model](https://mlsanity.com/paper/2501.12368/) (2025)
- [Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key](https://mlsanity.com/paper/2501.09695/) (2025)
- [Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback](https://mlsanity.com/paper/2412.15838/) (2024)
- [Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks](https://mlsanity.com/paper/2502.13175/) (2025)
- [ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2411.15268/) (2024)
- [A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications](https://mlsanity.com/paper/2410.15595/) (2024)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences](https://mlsanity.com/paper/2506.02095/) (2025)
- [Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization](https://mlsanity.com/paper/2411.10436/) (2024)
- [VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models](https://mlsanity.com/paper/2503.07478/) (2025)
- [Co-Reinforcement Learning for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2505.17534/) (2025)
- [BaseReward: A Strong Baseline for Multimodal Reward Model](https://mlsanity.com/paper/2509.16127/) (2025)
- [Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following](https://mlsanity.com/paper/2511.21662/) (2025)
- [DAMA: Data- and Model-aware Alignment of Multi-modal LLMs](https://mlsanity.com/paper/2502.01943/) (2025)
- [SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis](https://mlsanity.com/paper/2506.02096/) (2025)
- [From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models](https://mlsanity.com/paper/2503.06260/) (2025)
- [Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement](https://mlsanity.com/paper/2504.02906/) (2025)
- [MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions](https://mlsanity.com/paper/2507.21503/) (2025)
- [Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences](https://mlsanity.com/paper/2510.23451/) (2025)
- [Anyprefer: An Agentic Framework for Preference Data Synthesis](https://mlsanity.com/paper/2504.19276/) (2025)
- [A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy](https://mlsanity.com/paper/2506.09420/) (2025)
- [Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens](https://mlsanity.com/paper/2508.02419/) (2025)
- [MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding](https://mlsanity.com/paper/2512.06581/) (2025)
- [Systematic Reward Gap Optimization for Mitigating VLM Hallucinations](https://mlsanity.com/paper/2411.17265/) (2024)
- [Self-Improving VLM Judges Without Human Annotations](https://mlsanity.com/paper/2512.05145/) (2025)
- [Self-Improvement in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2510.02665/) (2025)
- [Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models](https://mlsanity.com/paper/2504.08809/) (2025)
- [Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models](https://mlsanity.com/paper/2411.04291/) (2024)
- [Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput](https://mlsanity.com/paper/2505.09498/) (2025)

## Abstract (arXiv)

As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial. However, the creation of such data with human supervision proves costly and time-intensive. In this paper, we investigate the efficacy of AI feedback to scale supervision for aligning LVLMs. We introduce VLFeedback, the first large-scale vision-language feedback dataset, comprising over 82K multi-modal instructions and comprehensive rationales generated by off-the-shelf models without human annotations. To evaluate the effectiveness of AI feedback for vision-language alignment, we train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback. Silkie showcases exceptional performance regarding helpfulness, visual faithfulness, and safety metrics. It outperforms its base model by 6.9% and 9.5% in perception and cognition tasks, reduces hallucination issues on MMHal-Bench, and exhibits enhanced resilience against red-teaming attacks. Furthermore, our analysis underscores the advantage of AI feedback, particularly in fostering preference diversity to deliver more comprehensive improvements. Our dataset, training code and models are available at https://vlf-silkie.github.io.