A Multimodal Recaptioning Framework To Account For Perceptual Diversity Across Languages In Vision-language Modeling

Abstract

When captioning an image, people describe objects in diverse ways, such as by using different terms and/or including details that are perceptually noteworthy to them. Descriptions can be especially unique across languages and cultures. Modern vision-language models (VLMs) gain understanding of images with text in different languages often through training on machine translations of English captions. However, this process relies on input content written from the perception of English speakers, leading to a perceptual bias. In this work, we outline a framework to address this bias. We specifically use a small amount of native speaker data, nearest-neighbor example guidance, and multimodal LLM reasoning to augment captions to better reflect descriptions in a target language. When adding the resulting rewrites to multilingual CLIP finetuning, we improve on German and Japanese text-image retrieval case studies (up to +3.5 mean recall, +4.4 on native vs. translation errors). We also propose

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybuettner2025a

Related papers

• Linear Alignment Of Vision-language Models For Image Captioning (2023)0.00
• Modeling Caption Diversity In Contrastive Vision-language Pretraining (2024)0.00
• Multilingual Diversity Improves Vision-language Representations (2024)2.26
• LLM2CLIP: Powerful Language Model Unlocks Richer Cross-modality Representation (2024)2.26
• Vlm4rec: Multimodal Semantic Representation For Recommendation With Large Vision-language Models (2026)1.82
• Mllms-augmented Visual-language Representation Learning (2023)0.00
• A Little More Like This: Text-to-image Retrieval With Vision-language Models Using Relevance Feedback (2025)0.00
• Contrasting Intra-modal And Ranking Cross-modal Hard Negatives To Enhance Visio-linguistic Compositional Understanding (2023)12.11