# SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning

arXiv: https://arxiv.org/abs/2508.06125 · HTML: https://mlsanity.com/paper/2508.06125/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 56 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 30 of 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [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)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [Attention on Attention for Image Captioning](https://mlsanity.com/paper/1908.06954/) (2019)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Connecting Vision and Language with Localized Narratives](https://mlsanity.com/paper/1912.03098/) (2019)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024)
- [DOCCI: Descriptions of Connected and Contrasting Images](https://mlsanity.com/paper/2404.19753/) (2024)
- [Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models](https://mlsanity.com/paper/2409.10695/) (2024)

## Built on by (most cited first, 16 of 16)

- [TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2512.03963/) (2025)
- [PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection](https://mlsanity.com/paper/2509.26272/) (2025)
- [ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison](https://mlsanity.com/paper/2605.20278/) (2026)
- [BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning](https://mlsanity.com/paper/2605.07394/) (2026)
- [MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites](https://mlsanity.com/paper/2510.12126/) (2025)
- [ReflectCAP: Detailed Image Captioning with Reflective Memory](https://mlsanity.com/paper/2604.12357/) (2026)
- [VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning](https://mlsanity.com/paper/2605.28023/) (2026)
- [Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning](https://mlsanity.com/paper/2603.01696/) (2026)
- [Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts](https://mlsanity.com/paper/2604.18091/) (2026)
- [Evaluating Remote Sensing Image Captions Beyond Metric Biases](https://mlsanity.com/paper/2604.22855/) (2026)
- [Clinically Structured Surrogate Rewards for Post-SFT Medical Image Captioning](https://mlsanity.com/paper/2608.18654/) (2026)
- [Re3Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning](https://mlsanity.com/paper/2608.21305/) (2026)
- [Controllable Image Captioning with Prompt-Conditioned Scene Rewards](https://mlsanity.com/paper/2609.00709/) (2026)
- [Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding](https://mlsanity.com/paper/2609.19767/) (2026)
- [Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint](https://mlsanity.com/paper/2609.19812/) (2026)
- [MGRL-RSCC: Multi-Granularity Reward Reinforcement Learning for Fine-Grained Remote Sensing Change Captioning](https://mlsanity.com/paper/2609.26166/) (2026)

## Abstract (arXiv)

We propose SC-Captioner, a reinforcement learning framework that enables the self-correcting capability of image caption models. Our crucial technique lies in the design of the reward function to incentivize accurate caption corrections. Specifically, the predicted and reference captions are decomposed into object, attribute, and relation sets using scene-graph parsing algorithms. We calculate the set difference between sets of initial and self-corrected captions to identify added and removed elements. These elements are matched against the reference sets to calculate correctness bonuses for accurate refinements and mistake punishments for wrong additions and removals, thereby forming the final reward. For image caption quality assessment, we propose a set of metrics refined from CAPTURE that alleviate its incomplete precision evaluation and inefficient relation matching problems. Furthermore, we collect a fine-grained annotated image caption dataset, RefinedCaps, consisting of 6.5K diverse images from COCO dataset. Experiments show that applying SC-Captioner on large visual-language models can generate better image captions across various scenarios, significantly outperforming the direct preference optimization training strategy.