OpenBMB 提出 Trident 解决多模态检索的文本偏好问题
OpenBMB 提出 Trident 解决多模态检索文本偏好问题
OpenBMB 提出 Trident，用多正样本视图 InfoNCE 联合训练文本、图像、融合三种视图，解决多模态检索器在图文混合语料上性能骤降的“Chaos in the Text”现象。
OpenBMB· @OpenBMB · X·2026-10-19 21:30· 54 分钟前AI 评分40
AI 导读
面壁智能 OpenBMB 提出 Trident，用多正样本视图 InfoNCE 联合训练文本、图像、融合三种视图，解决多模态检索器在图文混合语料上性能骤降的“Chaos in the Text”现象。
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
来源：RadarAI · aihot.news