Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components

TL;DR

Engineering conversational search systems addresses how to operationalize interactive information retrieval. Through a systematic literature review, it identifies four key CSS properties, proposes a six-layer architecture, and details seven core functional components that translate theory into practice. It further analyzes how large language models can augment CSS across query processing, retrieval, and generation, discussing capabilities, limitations, and mitigation strategies. The work provides a practical blueprint for designing scalable, real-world CSS and highlights promising directions for integrating LLMs without replacing modular architectures.

Abstract

Conversational search systems enable information retrieval via natural language interactions, with the goal of maximizing users' information gain over multiple dialogue turns. The increasing prevalence of conversational interfaces adopting this search paradigm challenges traditional information retrieval approaches, stressing the importance of better understanding the engineering process of developing these systems. We undertook a systematic literature review to investigate the links between theoretical studies and technical implementations of conversational search systems. Our review identifies real-world application scenarios, system architectures, and functional components. We consolidate our results by presenting a layered architecture framework and explaining the core functions of conversational search systems. Furthermore, we reflect on our findings in light of the rapid progress in large language models, discussing their capabilities, limitations, and directions for future research.

Figures (1)

• Figure 1: Architectural framework of conversational search systems.