CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning

2026-02-25 · Zhijiang Tang, Linhua Wang, Jiaxin Qi, Weihao Jiang, Peng Hou, Anxiang Zeng, Jianqiang Huang arxiv

Image captioning remains a fundamental task for vision language understanding, yet ground-truth supervision still relies predominantly on human-annotated references. Because human annotations reflect subjective preferences and expertise, ground-truth captions are often incomplete or even incorrect, which in turn limits caption models. We argue that caption quality should be assessed by two objective aspects: completeness (does the caption cover all salient visual facts?) and correctness (are the descriptions true with respect to the image?). To this end, we introduce CCCaption: a dual-reward reinforcement learning framework with a dedicated fine-tuning corpus that explicitly optimizes these properties to generate \textbf{C}omplete and \textbf{C}orrect \textbf{Captions}. For completeness, we use diverse LVLMs to disentangle the image into a set of visual queries, and reward captions that answer more of these queries, with a dynamic query sampling strategy to improve training efficiency. For correctness, we penalize captions that contain hallucinations by validating the authenticity of sub-caption queries, which are derived from the caption decomposition. Our symmetric dual-reward optimization jointly maximizes completeness and correctness, guiding models toward captions that better satisfy these objective criteria. Extensive experiments across standard captioning benchmarks show consistent improvements, offering a principled path to training caption models beyond human-annotation imitation.

📄 PDF Abstract BibTeX arXiv:2602.21655

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning Image Captioning

Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness

2026-04-20 · Mengzhao Jia, Zhihan Zhang, Meng Jiang arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incomplete derivations, weak evidence, or state…

Reinforcement Learning Multimodal Reasoning

TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

2026-06-30 · Yuanda Xu, Zhengze Zhou, Hejian Sang, Xiaomin Li 외 hf

Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uni…

Reinforcement Learning

Reinforcement Learning for Transition-Based Mention Detection

2017-03-13 · Georgiana Dinu, Wael Hamza, Radu Florian

This paper describes an application of reinforcement learning to the mention detection task. We define a novel action-based formulation for the mention detection task, in which a model can flexibly revise past labeling d…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference

2025-03-01 · Wenjie Qiu, Yi-Chen Li, Xuqin Zhang, Tianyi Zhang 외

Learning reward models from human preference datasets and subsequently optimizing language models via reinforcement learning has emerged as a fundamental paradigm for aligning LLMs with human preferences. The performance…

Sentence

The Emergence of Individuality in Multi-Agent Reinforcement Learning

2020-09-28 · Jiechuan Jiang, Zongqing Lu

Individuality is essential in human society, which induces the division of labor and thus improves the efficiency and productivity. Similarly, it should also be a key to multi-agent cooperation. Inspired by that individu…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)