A Survey of Conversational Search

2024-10-21

arXiv.org

AI Summary

This paper addresses the rigidity of traditional search engines and their inability to support complex, multi-turn information retrieval. Methodologically, it presents a comprehensive survey of large language model (LLM)-driven conversational search, offering the first unified analysis framework—spanning over 50 studies—that systematically charts architectural evolution, integrating dialogue state tracking, retrieval-augmented generation (RAG), multi-turn intent modeling, and established benchmarks (e.g., TREC CAsT, ConvER). Its core contributions are threefold: (1) a modular evaluation framework that clarifies the interplay among key components—query reformulation, search clarification, conversational retrieval, and response generation; (2) identification of three critical research directions: enhanced interpretability, standardized evaluation protocols, and robustness in real-world deployment; and (3) a call for consensus between academia and industry on design principles and evaluation criteria for conversational search systems.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

As a cornerstone of modern information access, search engines have become indispensable in everyday life. With the rapid advancements in AI and natural language processing (NLP) technologies, particularly large language models (LLMs), search engines have evolved to support more intuitive and intelligent interactions between users and systems. Conversational search, an emerging paradigm for next-generation search engines, leverages natural language dialogue to facilitate complex and precise information retrieval, thus attracting significant attention. Unlike traditional keyword-based search engines, conversational search systems enhance user experience by supporting intricate queries, maintaining context over multi-turn interactions, and providing robust information integration and processing capabilities. Key components such as query reformulation, search clarification, conversational retrieval, and response generation work in unison to enable these sophisticated interactions. In this survey, we explore the recent advancements and potential future directions in conversational search, examining the critical modules that constitute a conversational search system. We highlight the integration of LLMs in enhancing these systems and discuss the challenges and opportunities that lie ahead in this dynamic field. Additionally, we provide insights into real-world applications and robust evaluations of current conversational search systems, aiming to guide future research and development in conversational search.

Problem

• Exploring conversational search advancements and future directions
• Enhancing search systems with large language models (LLMs)
• Addressing challenges in multi-turn, context-aware information retrieval

Innovation

• Leverages natural language dialogue for search
• Integrates large language models (LLMs)
• Supports multi-turn contextual interactions