🔱 Why can irrelevant text outrank an image that actually contains the answer?
摘要
OpenBMB 发现多模态检索器在纯文本和纯图像语料上表现良好，但在图文混合语料上明显退化，并将这一现象称为 Chaos in the Text。分析显示存在系统性的模态偏好：文本常比语义对齐的图像获得更高相似度分数。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
🔱 Why can irrelevant text outrank an image that actually contains the answer?
We find that multimodal retrievers can perform well on text-only and image-only corpora, yet degrade sharply when text and images are mixed.
We call this phenomenon "Chaos in the Text."
Our analysis reveals a systematic Modality Preference: text often receives higher similarity scores than semantically aligned images. We introduce Trident, which jointly trains Text / Image / Fused views with Multi-Positive View InfoNCE.
On 6 visual-document retrieval benchmarks, Trident-Qwen3VL-2B improves Mix Avg NDCG@10 from 40.12 → 73.90.
📄 Paper/Project: https://chaos-in-texts.github.io/
💻 Code: https://github.com/OpenBMB/Trident
#MultimodalRetrieval #MultimodalRAG #RAG #VLM #Embedding #Trident #ChaosInTheText #OpenBMB
来源：OpenBMB · x.com
引用原文
OpenBMB. 🔱 Why can irrelevant text outrank an image that actually contains the answer?[EB/OL]. (2026-10-19)[访问日期]. https://x.com/OpenBMB/status/2112174429845504472.