Efficient Temporal-aware Matryoshka Adaptation For Temporal Information Retrieval

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuynh2026efficient

Related papers

• Matryoshka Representation Learning (2022)12.37
• 2D Matryoshka Training For Information Retrieval (2024)4.06
• Tempretriever: Fusion-based Temporal Dense Passage Retrieval For Time-sensitive Questions (2025)0.00
• Recurrence Meets Transformers For Universal Multimodal Retrieval (2025)2.41
• Matryoshka-adaptor: Unsupervised And Supervised Tuning For Smaller Embedding Dimensions (2024)2.26
• SMEC: Rethinking Matryoshka Representation Learning For Retrieval Embedding Compression (2025)0.00
• Metaembed: Scaling Multimodal Retrieval At Test-time With Flexible Late Interaction (2025)2.35
• Self-aware Vector Embeddings For Retrieval-augmented Generation: A Neuroscience-inspired Framework For Temporal, Confidence-weighted, And Relational Knowledge (2026)0.00