Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 56 of its 109 references that are in the map. First posted on arXiv 1 Jul 2024.
Builds on
56 of 109 references.
References · 56
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
- 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
- 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
- 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
- 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
- 2019Passage Re-ranking with BERTcited by 629
- 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
- 2018QuAC : Question Answering in Contextcited by 379
- 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
- 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 183
38 more
- 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 155
- 2020A Survey on Conversational Recommender Systemscited by 142
- 2019Asking Clarifying Questions in Open-Domain Information-Seeking Conversationscited by 136
- 2020Question Rewriting for Conversational Question Answeringcited by 93
- 2021Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Textcited by 89
- 2019Proactive Human-Machine Conversation with Explicit Conversation Goalscited by 87
- 2020Few-Shot Generative Conversational Query Rewritingcited by 85
- 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 74
- 2022RankGen: Improving Text Generation with Large Ranking Modelscited by 72
- 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
- 2022CLAM: Selective Clarification for Ambiguous Questions with Generative Language Modelscited by 66
- 2020TREC CAsT 2019: The Conversational Assistance Track Overviewcited by 64
- 2023Leveraging Large Language Models in Conversational Recommender Systemscited by 63
- 2020Query Resolution for Conversational Search with Limited Supervisioncited by 52
- 2019Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansioncited by 42
- 2023Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answeringcited by 41
- 2022A Decade of Knowledge Graphs in Natural Language Processing: A Surveycited by 40
- 2018Analyzing and Characterizing User Intent in Information-seeking Conversationscited by 36
- 2021Contextualized Query Embeddings for Conversational Searchcited by 36
- 2017Learning to Attend, Copy, and Generate for Session-Based Query Suggestioncited by 22
- 2022QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillationcited by 21
- 2020Summarizing and Exploring Tabular Data in Conversational Searchcited by 19
- 2020Fluent Response Generation for Conversational Question Answeringcited by 15
- 2019Conversational Product Search Based on Negative Feedbackcited by 13
- 2021Analysing Mixed Initiatives and Search Strategies during Conversational Searchcited by 12
- 2020Conversations with Search Engines: SERP-based Conversational Response Generationcited by 11
- 2021Wizard of Search Engine: Access to Information Through Conversations with Search Enginescited by 11
- 2019Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrievalcited by 10
- 2020Bias in Conversational Search: The Double-Edged Sword of the Personalized Knowledge Graphcited by 10
- 2021A Large-Scale Analysis of Mixed Initiative in Information-Seeking Dialogues for Conversational Searchcited by 9
- 2023Investigating Conversational Search Behavior For Domain Explorationcited by 9
- 2019Macaw: An Extensible Conversational Information Seeking Platformcited by 8
- 2021Controlling the Risk of Conversational Search via Reinforcement Learningcited by 8
- 2023Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understandingcited by 8
- 2021End-to-End Conversational Search for Online Shopping with Utterance Transfercited by 7
- 2022Simulating and Modeling the Risk of Conversational Searchcited by 6
- 2024A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generationcited by 6
- 2015What Users See - Structures in Search Engine Results Pagescited by 3
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.