Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912811056103424 |
|---|---|
| author | Huynh, Tuan-Luc Wang, Weiqing Le, Trung Vu, Thuy-Trang Gašević, Dragan Li, Yuan-Fang Do, Thanh-Toan |
| author_facet | Huynh, Tuan-Luc Wang, Weiqing Le, Trung Vu, Thuy-Trang Gašević, Dragan Li, Yuan-Fang Do, Thanh-Toan |
| contents | Retrievers are a key bottleneck in Temporal Retrieval-Augmented Generation (RAG) systems: failing to retrieve temporally relevant context can degrade downstream generation, regardless of LLM reasoning. We propose Temporal-aware Matryoshka Representation Learning (TMRL), an efficient method that equips retrievers with temporal-aware Matryoshka embeddings. TMRL leverages the nested structure of Matryoshka embeddings to introduce a temporal subspace, enhancing temporal encoding while preserving general semantic representations. Experiments show that TMRL efficiently adapts diverse text embedding models, achieving competitive temporal retrieval and temporal RAG performance compared to prior Matryoshka-based non-temporal methods and prior temporal methods, while enabling flexible accuracy-efficiency trade-offs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05549 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval Huynh, Tuan-Luc Wang, Weiqing Le, Trung Vu, Thuy-Trang Gašević, Dragan Li, Yuan-Fang Do, Thanh-Toan Information Retrieval Retrievers are a key bottleneck in Temporal Retrieval-Augmented Generation (RAG) systems: failing to retrieve temporally relevant context can degrade downstream generation, regardless of LLM reasoning. We propose Temporal-aware Matryoshka Representation Learning (TMRL), an efficient method that equips retrievers with temporal-aware Matryoshka embeddings. TMRL leverages the nested structure of Matryoshka embeddings to introduce a temporal subspace, enhancing temporal encoding while preserving general semantic representations. Experiments show that TMRL efficiently adapts diverse text embedding models, achieving competitive temporal retrieval and temporal RAG performance compared to prior Matryoshka-based non-temporal methods and prior temporal methods, while enabling flexible accuracy-efficiency trade-offs. |
| title | Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.05549 |