RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge

2025-10-15

AI Summary

Existing RAG systems neglect the temporal sensitivity of knowledge, hindering accurate discrimination of time-sensitive facts; moreover, their evaluation predominantly relies on static corpora, overlooking update costs and retrieval stability during knowledge evolution. To address these limitations, we propose TG-RAG, a time-aware RAG framework featuring a dual-layer temporal graph model—comprising a temporal knowledge graph and a hierarchical time tree—to explicitly encode multi-granular temporal knowledge. TG-RAG introduces three key innovations: timestamped relation extraction, dynamic subgraph retrieval, and incremental graph fusion—enabling fine-grained temporal-aware retrieval and efficient incremental updates. Evaluated on the newly constructed ECT-QA benchmark—a temporally evolving question-answering dataset—TG-RAG significantly outperforms state-of-the-art baselines in both time-sensitive question answering and incremental update efficiency.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Temporal Planning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Knowledge is inherently time-sensitive and continuously evolves over time. Although current Retrieval-Augmented Generation (RAG) systems enrich LLMs with external knowledge, they largely ignore this temporal nature. This raises two challenges for RAG. First, current RAG methods lack effective time-aware representations. Same facts of different time are difficult to distinguish with vector embeddings or conventional knowledge graphs. Second, most RAG evaluations assume a static corpus, leaving a blind spot regarding update costs and retrieval stability as knowledge evolves. To make RAG time-aware, we propose Temporal GraphRAG (TG-RAG), which models external corpora as a bi-level temporal graph consisting of a temporal knowledge graph with timestamped relations and a hierarchical time graph. Multi-granularity temporal summaries are generated for each time node to capture both key events and broader trends at that time. The design supports incremental updates by extracting new temporal facts from the incoming corpus and merging them into the existing graph. The temporal graph explicitly represents identical facts at different times as distinct edges to avoid ambiguity, and the time hierarchy graph allows only generating reports for new leaf time nodes and their ancestors, ensuring effective and efficient updates. During inference, TG-RAG dynamically retrieves a subgraph within the temporal and semantic scope of the query, enabling precise evidence gathering. Moreover, we introduce ECT-QA, a time-sensitive question-answering dataset featuring both specific and abstract queries, along with a comprehensive evaluation protocol designed to assess incremental update capabilities of RAG systems. Extensive experiments show that TG-RAG significantly outperforms existing baselines, demonstrating the effectiveness of our method in handling temporal knowledge and incremental updates.

Problem

• Addressing time-aware representation challenges in RAG systems
• Solving incremental update efficiency for evolving knowledge bases
• Improving temporal query handling through dynamic evidence retrieval

Innovation

• Models corpora as bi-level temporal graph with timestamped relations
• Generates multi-granularity temporal summaries for time nodes
• Supports incremental updates by merging new facts into graph