A Survey of Model Architectures in Information Retrieval
This forum post introduces and annotates the survey "A Survey of Model Architectures in Information Retrieval" (arXiv:2502.14822, published 2025-02-20), by Zhichao Xu, Fengran Mo, Zhiqi Huang, Crystina Zhang, Puxuan Yu, Bei Wang, et al. (8 authors total).
Original Abstract
> The period from 2019 to the present marks one of the most significant paradigm shifts in information retrieval (IR) and natural language processing (NLP), culminating in the emergence of powerful large language models (LLMs) from 2022 onward. Methods based on pretrained encoder-only architectures (e.g., BERT) as well as decoder-only generative LLMs have outperformed many earlier approaches, demonstrating particularly strong performance in zero-shot scenarios and complex reasoning tasks. This survey examines the evolution of model architectures in IR, with a focus on two key aspects: backbone models for feature extraction and end-to-end system architectures for relevance estimation. To maintain analytical clarity, we deliberately separate architectural design from training methodologies, enabling a focused examination of structural innovations in IR systems. We trace the progression from traditional term-based retrieval models to modern neural approaches, highlighting the transformative impact of transformer-based architectures and subsequent LLM developments. The survey concludes with a forward-looking discussion of open challenges and emerging research directions, including architectural optimization for efficiency and scalability, robust handling of multimodal and multilingual data, and adaptation to novel application domains such as autonomous search agents, which may represent the next paradigm in IR.
Core Contributions
- Provides a unifying perspective that organizes dispersed related work into a comparable framework.
- Decomposes method components (representation learning, retrievers, rerankers, planners, generators, feedback mechanisms) for easier engineering adoption.
- Offers reproducible benchmarks, datasets, and taxonomy tables, lowering entry barriers for new researchers.
- Discusses interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, outlining migration paths from research prototypes to industrial systems.
- Identifies open problems: evaluation credibility, latency and cost, hallucination and safety, cross-lingual and multimodal extension.
- Dense retrieval: high recall, low latency; suited for first-stage retrieval.
- Late interaction (e.g., ColBERT): higher accuracy but larger indexes.
- Generative IR: directly "generates" documents via tokens or docids, simplifying cascades.
- Agentic search: models search as sequential decision-making, supporting multi-hop reasoning and self-reflection.
- 2019–2021: BERT reranking and DPR establish neural retrieval foundations.
- 2022–2023: RAG and FreshLLM drive retrieval-generation fusion.
- 2024 onward: conversational/agentic search and Gen-RecSys explode.
- 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth frontiers.
- Datasets: MS MARCO, BEIR, Natural Questions, domain corpora, recommendation sets.
- Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, token cost.
- Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, commercial search APIs.
- Ablations: contributions of retrieval steps, reranking depth, and training data scale.
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search (arXiv:2510.16724)
- A Survey of Conversational Search (arXiv:2410.15576, Oct 2024)
- A Survey of LLM-Empowered Agents for Recommendation (arXiv:2503.05659)
- A Survey on AI Search with Large Language Models (July 2025)
- A Survey on Knowledge-Oriented Retrieval-Augmented Generation (arXiv:2503.10677)
- Cross-Modal Retrieval: A Systematic Review
Taxonomy
| Dimension | Sub-class | Representative ideas | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Dual-tower, cross-encoder, DSI, GPT indexing | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization objectives | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Annotation scarcity | | Evaluation | Offline / Online / Human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Diverges from true satisfaction |
Four Main Research Lines
Timeline of Evolution
Evaluation Paradigm
Typical benchmarks and metrics covered by this line of surveys:
> Note: verify exact quantitative results against the original PDF; this post summarizes design logic from the abstract and public metadata.
Key Takeaways for Search / Rec / Personalization
1. Architecture: cascade retrieval + reranking + generation remains mainstream, but the agentic paradigm makes retrieval count and strategy themselves learnable. 2. Data: high-quality instruction data and click/session logs are equally critical; synthetic data must guard against 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, interpretability, and safety are hard constraints for industrial deployment—do not optimize only academic benchmarks.
Open Problems and Future Directions
Insufficient unified benchmarks, non-reproducible private data, LLM evaluation bias, and safety/cost constraints of agentic systems. Future work: finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, multimodal and cross-lingual consistency, better test-time compute allocation, deeper fusion with knowledge graphs, and causal/fairness constraints for recommendation.
Engineering Checklist
| Check | Question | Recommendation | |---|---|---| | Data | PII in training/index? Version control? | Partitioned indexes, anonymization, rollback-able embedding versions | | Latency | p99 budget? Retrieval steps? | Cascade + early stopping, hot-query caching, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation checks | | Safety | Poisoning/bias from open retrieval? | Source whitelists, adversarial detection, output filtering | | Cost | Token and GPU cost per query? | Small-model routing, distillation, sparse+dense hybrid |
Glossary
| Term | Meaning | |---|---| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain | | Agentic Search | Search modeled as sequential decision-making and tool calling | | Gen-IR | Generative Information Retrieval |