It's High Time: A Survey of Temporal Information Retrieval and Question Answering

2025-05-26

AI Summary

This paper addresses key challenges in temporal information processing—including temporal intent identification, temporal expression normalization, event chronology modeling, and dynamic fact reasoning—particularly for time-sensitive domains such as news, historical archives, and scientific literature. It provides a systematic survey of recent advances in Temporal Information Retrieval (TIR) and Temporal Question Answering (TQA), unifying traditional approaches with modern large language model (LLM)-driven techniques for chronological modeling, multi-hop temporal reasoning, and retrieval-augmented generation (RAG)-enhanced timely QA. The work introduces a novel evaluation paradigm centered on temporal robustness and constructs a spatiotemporal IR/TQA knowledge graph encompassing benchmark datasets, evaluation metrics, and methodological taxonomies. These contributions offer both theoretical foundations and practical guidelines for developing temporally aware AI systems.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Time plays a critical role in how information is generated, retrieved, and interpreted. In this survey, we provide a comprehensive overview of Temporal Information Retrieval and Temporal Question Answering, two research areas aimed at handling and understanding time-sensitive information. As the amount of time-stamped content from sources like news articles, web archives, and knowledge bases increases, systems must address challenges such as detecting temporal intent, normalizing time expressions, ordering events, and reasoning over evolving or ambiguous facts. These challenges are critical across many dynamic and time-sensitive domains, from news and encyclopedias to science, history, and social media. We review both traditional approaches and modern neural methods, including those that use transformer models and Large Language Models (LLMs). We also review recent advances in temporal language modeling, multi-hop reasoning, and retrieval-augmented generation (RAG), alongside benchmark datasets and evaluation strategies that test temporal robustness, recency awareness, and generalization.

Problem

• Surveying Temporal Information Retrieval and Question Answering challenges
• Addressing time-sensitive information handling in dynamic domains
• Reviewing modern neural methods for temporal language modeling

Innovation

• Survey of Temporal Information Retrieval and QA
• Transformer models and LLMs for time-sensitive tasks
• Temporal language modeling and multi-hop reasoning