OpenBMB 发现多模态检索"Chaos in the Text"问题，推出 Trident 检索器
OpenBMB 找到了图文混合检索掉分的原因：文本天然比图像得分高。他们的 Trident 模型把 NDCG 从 40 拉到 74，做 RAG 的可以看看。
OpenBMB 团队发现多模态检索器在纯文本或纯图像语料上表现正常，但在图文混合语料中性能急剧下降，并将其命名为"Chaos in the Text"。分析显示检索器存在系统性 Modality Preference，即文本获得的相似度分数普遍高于语义对齐的图像。团队提出的 Trident 采用 Multi-Positive View InfoNCE 联合训练文本、图像和融合三种视图。Trident-Qwen3VL-2B 在 6 个视觉文档检索基准上将 Mix Avg NDCG@10 从 40.12 提升到 73.90。
🔱 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://t.co/d9sAJY3UKe 💻 Code: https://t.co/H1L0QvkuUi
#MultimodalRetrieval #MultimodalRAG #RAG #VLM #Embedding #Trident #ChaosInTheText #OpenBMB
