From Matching to Generation: A Survey on Generative Information Retrieval
- Authors: Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yuyao Zhang, Peitian Zhang, Yutao Zhu, et al. (7 authors)
- Published: 2024-04-23
- Source: https://arxiv.org/abs/2404.14851
- Type: Survey
- Code: https://github.com/RUC-NLPIR/GenIR-Survey
- A unified perspective organizing scattered GenIR work into a comparable framework
- A clear decomposition of method components (representation learning, retrievers, rerankers, planners, generators, feedback mechanisms)
- A reproducible taxonomy, benchmarks, and classification tables lowering entry barriers for follow-up research
- Discussion of interfaces with LLM tool use, reinforcement learning, and multi-agent collaboration
- Explicit open problems: evaluation trustworthiness, latency/cost, hallucination and safety, cross-lingual and multimodal extension
- Dense retrieval: high recall, low latency; suitable for first-stage retrieval
- Late interaction (e.g., ColBERT): higher precision but larger indexes
- Generative IR: directly "generates" documents as tokens or docids, simplifying the cascade
- Agentic search: models search as sequential decision-making, supporting multi-hop and self-reflection
- 2019–2021: BERT reranking and DPR establish neural retrieval foundations
- 2022–2023: RAG and FreshLLMs drive retrieval–generation fusion
- 2024 onward: conversational/agentic search and generative recommender systems (Gen-RecSys) surge
- 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become growth areas
- Datasets: MS MARCO, BEIR, Natural Questions, domain corpora
- Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency and token cost
- Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, commercial search APIs
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search (arXiv:2510.16724)
- A Survey of Conversational Search (arXiv:2410.15576)
- 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)
Background & Motivation
Information Retrieval (IR) systems have long been dominated by traditional methods relying on similarity matching. With the advancement of pre-trained language models, generative information retrieval (GenIR) emerges as a novel paradigm. Traditional pipelines separate retrieval, ranking, and generation, which struggles to meet LLM-era demands for natural language interaction, multi-hop reasoning, and up-to-date knowledge.
Core Contributions
Taxonomy of GenIR
Based on the form of information provided to users, current research in GenIR falls into two branches:
1. Generative Document Retrieval (GR) — leverages the generative model's parameters for memorizing documents, enabling retrieval by directly generating relevant document identifiers without explicit indexing. Covered topics: model training and structure, document identifiers, incremental learning. 2. Reliable Response Generation — employs language models to directly generate the information users seek, breaking traditional IR's limits in document granularity and relevance matching while offering flexibility, efficiency, and creativity. Covered topics: internal knowledge memorization, external knowledge augmentation.
Four Research Lines in Modern Search
Timeline of Evolution
Evaluation Paradigms
Key Takeaways
1. Architecture: cascade retrieval + rerank + generation remains mainstream, but agentic paradigms make retrieval strategy itself learnable 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data risks leakage and distribution shift 3. Evaluation: the gap between offline metrics and online satisfaction widens; LLM-as-judge needs cross-validation with human evaluation 4. Product: latency, cost, explainability, and safety are hard constraints for industrial deployment
Open Problems & Future Directions
Unified benchmarks, reproducibility of private data, LLM evaluation bias, and safety/cost constraints of agentic systems remain open. Future work includes finer-grained process supervision, joint retrieval–reasoning training, enterprise metadata governance, and multimodal/cross-lingual consistency.
Abstract (original, verbatim)
> Information Retrieval (IR) systems are crucial tools for users to access information, which have long been dominated by traditional methods relying on similarity matching. With the advancement of pre-trained language models, generative information retrieval (GenIR) emerges as a novel paradigm, attracting increasing attention. Based on the form of information provided to users, current research in GenIR can be categorized into two aspects: (1) Generative Document Retrieval (GR) leverages the generative model's parameters for memorizing documents, enabling retrieval by directly generating relevant document identifiers without explicit indexing. (2) Reliable Response Generation employs language models to directly generate information users seek, breaking the limitations of traditional IR in terms of document granularity and relevance matching while offering flexibility, efficiency, and creativity to meet practical needs. This paper aims to systematically review the latest research progress in GenIR... This review aims to offer a comprehensive reference for researchers, encouraging further development in the GenIR field.