# Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning

arXiv: https://arxiv.org/abs/2503.07906 · HTML: https://mlsanity.com/paper/2503.07906/

## Key facts

- Cited by 25 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 49 of its 62 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## 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 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)

## Built on by (most cited first, 25 of 25)

- [Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences](https://mlsanity.com/paper/2506.02095/) (2025)
- [SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning](https://mlsanity.com/paper/2508.06125/) (2025)
- [CaptionQA: Is Your Caption as Useful as the Image Itself?](https://mlsanity.com/paper/2511.21025/) (2025)
- [Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following](https://mlsanity.com/paper/2511.21662/) (2025)
- [LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs](https://mlsanity.com/paper/2602.00462/) (2026)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward](https://mlsanity.com/paper/2508.18634/) (2025)
- [PhyCritic: Multimodal Critic Models for Physical AI](https://mlsanity.com/paper/2602.11124/) (2026)
- [Cross-Image Contrastive Decoding: Precise, Lossless Suppression of Language Priors in Large Vision-Language Models](https://mlsanity.com/paper/2505.10634/) (2025)
- [CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning](https://mlsanity.com/paper/2602.21655/) (2026)
- [JEEM: Vision-Language Understanding in Four Arabic Dialects](https://mlsanity.com/paper/2503.21910/) (2025)
- [Panoptic Captioning: An Equivalence Bridge for Image and Text](https://mlsanity.com/paper/2505.16334/) (2025)
- [RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction](https://mlsanity.com/paper/2505.22613/) (2025)
- [SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation](https://mlsanity.com/paper/2509.03897/) (2025)
- [BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning](https://mlsanity.com/paper/2605.07394/) (2026)
- [MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning](https://mlsanity.com/paper/2508.21451/) (2025)
- [PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions](https://mlsanity.com/paper/2510.19060/) (2025)
- [VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning](https://mlsanity.com/paper/2605.28023/) (2026)
- [Probing the Limits of Stylistic Alignment in Vision-Language Models](https://mlsanity.com/paper/2509.25568/) (2025)
- [Reliability-Prioritized Fine-Grained Generation in Multimodal Large](https://mlsanity.com/paper/2606.29573/) (2026)
- [ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models](https://mlsanity.com/paper/2607.00361/) (2026)
- [Holo-Captioning: Toward the Text Equivalent of 3D Scenes](https://mlsanity.com/paper/2607.02908/) (2026)
- [A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss](https://mlsanity.com/paper/2609.00591/) (2026)
- [A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions](https://mlsanity.com/paper/2610.00952/) (2026)
- [Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels](https://mlsanity.com/paper/2610.16552/) (2026)

## Abstract (arXiv)

Image captioning has long been a pivotal task in visual understanding, with recent advancements in vision-language models (VLMs) significantly enhancing the ability to generate detailed image captions. However, the evaluation of detailed image captioning remains underexplored due to outdated evaluation metrics and coarse annotations. In this paper, we introduce DeCapBench along with a novel metric, DCScore, specifically designed for detailed captioning tasks. DCScore evaluates hallucinations and fine-grained comprehensiveness by deconstructing responses into the smallest self-sufficient units, termed primitive information units, and assessing them individually. Our evaluation shows that DCScore aligns more closely with human judgment than other rule-based or model-based metrics. Concurrently, DeCapBench exhibits a high correlation with VLM arena results on descriptive tasks, surpassing existing benchmarks for vision-language models. Additionally, we present an automatic fine-grained feedback collection method, FeedQuill, for preference optimization based on our advanced metric, showing robust generalization capabilities across auto-generated preference data. Extensive experiments on multiple VLMs demonstrate that our method not only significantly reduces hallucinations but also enhances performance across various benchmarks, achieving superior detail captioning performance while surpassing GPT-4o.