A Survey of Conversational Search
Overview
- Authors: Fengran Mo, Kelong Mao, Ziliang Zhao, Hongjin Qian, Haonan Chen, Yiruo Cheng, et al. (10 authors total)
- Published: 2024-10-21
- Source: https://arxiv.org/abs/2410.15576v1
- Type: Survey
- Unified perspective: Organizes scattered research on conversational search into a comparable framework, decomposing system components (representation learning, retriever, re-ranker, planner, generator, feedback mechanisms).
- Core modules examined: Query reformulation, search clarification, conversational retrieval, and response generation work together to enable multi-turn, context-aware interactions.
- LLM integration: Highlights how retrieval-augmented generation (RAG), agents, and tool use reshape the division of labor among retrieval, ranking, generation, and tool calling.
- Four main technical lines:
- Dense retrieval — high recall, low latency, suited for first-stage retrieval
- Late interaction (e.g., ColBERT) — higher precision but larger index
- Generative IR — generates documents via tokens or docids, simplifying the cascade
- Agentic search — models search as sequential decision-making supporting multi-hop reasoning and self-reflection
- 2019–2021: BERT re-ranking and DPR establish neural retrieval foundations
- 2022–2023: RAG and FreshLLMS drive retrieval-generation fusion
- 2024: Conversational/agentic search and generative recommendation surge
- 2025–2026 (anticipated): RL-trained search agents, Deep Research, and GraphRAG as growth frontiers
- Datasets: MS MARCO, BEIR, Natural Questions, domain corpora
- Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, token cost
- Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs
- The survey notes a widening gap between offline metrics and online satisfaction; LLM-as-judge should be cross-validated with human assessment.
- Lack of unified benchmarks; private data hinders reproducibility
- Bias in LLM-based evaluation
- Safety and cost constraints for agentic systems operating on the open web
- Future work: finer-grained process supervision, retrieval-reasoning co-training, multimodal and cross-lingual consistency, deeper fusion with knowledge graphs and structured databases
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search (arXiv 2510.16724)
- A Survey of LLM-Empowered Agents for Recommendation (arXiv 2503.05659)
- A Survey of Model Architectures in Information Retrieval (arXiv 2502.14822)
- A Survey on Knowledge-Oriented Retrieval-Augmented Generation (arXiv 2503.10677)
- Cross-Modal Retrieval: A Systematic Review
Abstract (original)
> 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.
Key Points
Taxonomy
| Dimension | Subcategories | Representative ideas | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Dual encoders, cross-encoders, DSI | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization goals | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce annotations | | Evaluation | Offline / online / human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Gap vs. real user satisfaction |
Timeline of Evolution
Evaluation Landscape
Conclusions and Insights
1. Architecture: Cascade retrieval + re-ranking + generation remains mainstream, but the agentic paradigm makes the number and policy of retrieval steps itself learnable. 2. Data: High-quality instruction data and click/session logs are critical; synthetic data requires care against leakage and distribution shift. 3. Evaluation: Offline metrics increasingly diverge from online satisfaction; process-level metrics (citation accuracy, multi-hop chain completeness) are gaining importance. 4. Deployment: Latency, cost, interpretability, and safety are hard production constraints, not just academic benchmark numbers.