# FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback

arXiv: https://arxiv.org/abs/2404.05046 · HTML: https://mlsanity.com/paper/2404.05046/

## Key facts

- Cited by 30 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 37 of its 49 references that are in the map.
- First posted on arXiv 7 Apr 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 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023)
- [MultiModal-GPT: A Vision and Language Model for Dialogue with Humans](https://mlsanity.com/paper/2305.04790/) (2023)
- [Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://mlsanity.com/paper/2306.04488/) (2023)
- [Woodpecker: Hallucination Correction for Multimodal Large Language Models](https://mlsanity.com/paper/2310.16045/) (2023)
- [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024)
- [Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards](https://mlsanity.com/paper/2402.18571/) (2024)

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

- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2406.11839/) (2024)
- [VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models](https://mlsanity.com/paper/2411.17451/) (2024)
- [Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement](https://mlsanity.com/paper/2405.15973/) (2024)
- [Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection](https://mlsanity.com/paper/2412.13817/) (2024)
- [Automated Multi-level Preference for MLLMs](https://mlsanity.com/paper/2405.11165/) (2024)
- [Mitigating Object Hallucinations via Sentence-Level Early Intervention](https://mlsanity.com/paper/2507.12455/) (2025)
- [AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs](https://mlsanity.com/paper/2501.02135/) (2025)
- [Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification](https://mlsanity.com/paper/2407.02352/) (2024)
- [TLDR: Token-Level Detective Reward Model for Large Vision Language Models](https://mlsanity.com/paper/2410.04734/) (2024)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (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)
- [From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2410.06795/) (2024)
- [A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2505.01958/) (2025)
- [Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation](https://mlsanity.com/paper/2512.00706/) (2025)
- [FIHA: Autonomous Hallucination Evaluation in Vision-Language Models with Davidson Scene Graphs](https://mlsanity.com/paper/2409.13612/) (2024)
- [A Unified Hallucination Mitigation Framework for Large Vision-Language Models](https://mlsanity.com/paper/2409.16494/) (2024)
- [LDC: Learning to Generate Research Idea with Dynamic Control](https://mlsanity.com/paper/2412.14626/) (2024)
- [Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization](https://mlsanity.com/paper/2412.16232/) (2024)
- [Multimodal Reference Visual Grounding](https://mlsanity.com/paper/2504.02876/) (2025)
- [SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision](https://mlsanity.com/paper/2508.03177/) (2025)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing](https://mlsanity.com/paper/2508.01653/) (2025)
- [Suppressing VLM Hallucinations with Spectral Representation Filtering](https://mlsanity.com/paper/2511.12220/) (2025)
- [SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding](https://mlsanity.com/paper/2602.09825/) (2026)
- [Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification](https://mlsanity.com/paper/2603.24058/) (2026)
- [Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency Constraints](https://mlsanity.com/paper/2607.21722/) (2026)
- [Wiener Representation Filtering for VLM Hallucination Suppression](https://mlsanity.com/paper/2608.08167/) (2026)

## Abstract (arXiv)

Large Vision-Language Models (LVLMs) have demonstrated proficiency in tackling a variety of visual-language tasks. However, current LVLMs suffer from misalignment between text and image modalities which causes three kinds of hallucination problems, i.e., object existence, object attribute, and object relationship. To tackle this issue, existing methods mainly utilize Reinforcement Learning (RL) to align modalities in LVLMs. However, they still suffer from three main limitations: (1) General feedback can not indicate the hallucination type contained in the response; (2) Sparse rewards only give the sequence-level reward for the whole response; and (3)Annotation cost is time-consuming and labor-intensive. To handle these limitations, we propose an innovative method to align modalities in LVLMs through Fine-Grained Artificial Intelligence Feedback (FGAIF), which mainly consists of three steps: AI-based Feedback Collection, Fine-grained Reward Model Training, and Reinforcement Learning with Fine-grained Reward. Specifically, We first utilize AI tools to predict the types of hallucination for each segment in the response and obtain a collection of fine-grained feedback. Then, based on the collected reward data, three specialized reward models are trained to produce dense rewards. Finally, a novel fine-grained feedback module is integrated into the Proximal Policy Optimization (PPO) algorithm. Extensive experiments are conducted on hallucination and general benchmarks, demonstrating the superior performance of our proposed method. Notably, compared with previous models trained with the RL-based aligning method, our proposed method is effective even with fewer parameters.