OpenBMB 提出 Trident 缓解多模态检索"文本混沌"
OpenBMB 提出多模态检索方法 Trident，通过 Multi-Positive View InfoNCE 联合训练 Text / Image / Fused 三种视图，缓解混合语料中文本相似度系统性压过图像的"Chaos in the Text"现象。
🔱 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: chaos-in-texts.github.io/
💻 Code: github.com/OpenBMB/Trident
#MultimodalRetrieval #MultimodalRAG #RAG #VLM #Embedding #Trident #ChaosInTheText #OpenBMB
来源：OpenBMB · x.com