Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908350307893248 |
|---|---|
| author | Ma, Xueguang Gao, Luyu Zhuang, Shengyao Zhan, Jiaqi Samantha Callan, Jamie Lin, Jimmy |
| author_facet | Ma, Xueguang Gao, Luyu Zhuang, Shengyao Zhan, Jiaqi Samantha Callan, Jamie Lin, Jimmy |
| contents | Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created new opportunities for multimodal retrieval. In response, we have updated the Tevatron toolkit, introducing a unified pipeline that enables researchers to explore retriever models at different scales, across multiple languages, and with various modalities. This demo paper highlights the toolkit's key features, bridging academia and industry by supporting efficient training, inference, and evaluation of neural retrievers. We showcase a unified dense retriever achieving strong multilingual and multimodal effectiveness, and conduct a cross-modality zero-shot study to demonstrate its research potential. Alongside, we release OmniEmbed, to the best of our knowledge, the first embedding model that unifies text, image document, video, and audio retrieval, serving as a baseline for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02466 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality Ma, Xueguang Gao, Luyu Zhuang, Shengyao Zhan, Jiaqi Samantha Callan, Jamie Lin, Jimmy Information Retrieval Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created new opportunities for multimodal retrieval. In response, we have updated the Tevatron toolkit, introducing a unified pipeline that enables researchers to explore retriever models at different scales, across multiple languages, and with various modalities. This demo paper highlights the toolkit's key features, bridging academia and industry by supporting efficient training, inference, and evaluation of neural retrievers. We showcase a unified dense retriever achieving strong multilingual and multimodal effectiveness, and conduct a cross-modality zero-shot study to demonstrate its research potential. Alongside, we release OmniEmbed, to the best of our knowledge, the first embedding model that unifies text, image document, video, and audio retrieval, serving as a baseline for future research. |
| title | Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2505.02466 |