Temporal Information Retrieval and Question Answering in the Age of LLMs

A Comprehensive Tutorial

WWW 2026 Conference | 13 April, 2026 | Dubai, UAE

Abstract

Time plays a crucial role in how we retrieve, interpret, and reason over information. As knowledge on the Web continuously evolves, information retrieval (IR) and question answering (QA) systems must recognize not only what is relevant but also when it is valid. This tutorial provides a comprehensive overview of Temporal Information Retrieval (TIR) and Temporal Question Answering (TQA), two closely related fields that address temporal relevance, reasoning, and adaptation in information access.

We trace the evolution of temporal methods from early rule-based and probabilistic approaches to modern transformer and large language model (LLM) architectures, highlighting how temporal modeling, reasoning, and retrieval-augmented generation (RAG) are reshaping the field. Participants will learn the fundamental principles of temporal IR/QA, explore pre-LLM and neural methods, and examine recent advances in temporal RAG and temporal reasoning over evolving knowledge.

The tutorial concludes with open challenges and future directions for building temporally robust and adaptive AI systems. By bridging classical IR concepts with modern LLM-based reasoning, this tutorial offers a timely and unified perspective on temporal information access for the evolving Web.

Tutorial Overview

                Key Topics Covered
                Fundamentals of Temporal Information Retrieval (TIR)
Temporal Question Answering (TQA) systems and architectures
Evolution from rule-based to probabilistic approaches
Modern transformer and LLM architectures for temporal reasoning
Temporal modeling and Retrieval-Augmented Generation (RAG)
Temporal reasoning over evolving knowledge
Recent advances and benchmarks in temporal IR/QA
Open challenges and future research directions

            

Target Audience

This tutorial is designed for researchers, practitioners, and graduate students interested in information retrieval, natural language processing, question answering, and large language models. Participants should have basic knowledge of NLP and machine learning concepts.

Learning Outcomes

After attending this tutorial, participants will be able to:

Understand the unique challenges of temporal information retrieval and question answering
Trace the evolution of temporal methods from classical to modern LLM-based approaches
Design and implement temporal QA systems using state-of-the-art techniques
Leverage LLMs and RAG for temporal reasoning tasks
Evaluate temporal IR and QA systems using standard benchmarks
Identify promising research directions and open challenges in temporal information access

Schedule

Duration: Half-day tutorial

1. Introduction and Motivation

Goal: Establish why time is a fundamental dimension in information access.

Why time matters in IR and QA: recency, evolution, factual decay
Key challenges: knowledge volatility, temporal ambiguity, context shift
Core definitions and taxonomy of temporal IR and QA

2. Core Concepts and Temporal IR Tasks)

Goal: Introduce canonical temporal tasks and benchmarks.

Temporal intent detection, document dating, focus time estimation
Temporal granularity and temporal query understanding
Benchmark overview: design and evaluation paradigms

3. Foundations: Pre-LLM Temporal IR Models

Goal: Review classical methods prior to the neural era.

Rule-based, statistical, and temporal language modeling approaches
Frameworks for temporal annotation and normalization
Temporal indexing and ranking strategies

4. Neural and Transformer-based Temporal Models

Goal: Explain the evolution of temporal representation learning.

Temporal language models
Temporal adaptation, continual learning, and timestamp conditioning
How neural encoders capture or forget temporal signals

Quick Q&A

All presenters

Clarify foundational concepts and prepare participants for the RAG and reasoning sections.

☕ Coffee Break

Informal networking and discussion

5. Temporal RAG and Reasoning

Goal: Explore retrieval and reasoning in LLM-based temporal systems.

Integrating temporal retrieval within LLM pipelines (Temporal RAG)
Temporal dense retrievers and alignment
Temporal reasoning: event ordering, duration inference, multi-hop reasoning
Benchmarks for evaluation and temporal reasoning limits of LLMs

6. Temporal Web and Evaluation Ecosystem

Goal: Connect temporal IR to the Web context and evaluation resources.

Temporal Web analytics and the TempWeb workshop legacy
Evaluating time-aware retrieval on dynamic and archived Web data
Datasets and tools for temporal QA and retrieval

7. Emerging Topics and Open Challenges)

Goal: Discuss open challenges and future directions.

Temporal uncertainty, diachronic–synchronic integration
Continual updates, temporally aware LLM agents, dynamic evaluation

8. Concluding Discussion and Q&A

Goal: Summarize insights and engage participants.

Key takeaways and conceptual synthesis
Interactive discussion on open research problems

Materials

All tutorial materials will be made available here before and after the tutorial.

Tutorial Speakers

Additional Resources

Key Papers

Coming soon - A curated list of key papers in temporal IR and QA will be added here.

Contact

For questions or inquiries about this tutorial, please contact:

📧 bhawna.piryani@uibk.ac.at (Bhawna Piryani)
📧 avishek.anand@tudelft.nl (Avishek Anand)
📧 adam.jatowt@uibk.ac.at (Adam Jatowt)