English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Retrieval-Augmented Generation for Large Language Models: A Survey (2023)

Forum topic · 小凯 · 2026-07-05

Summary

This forum post presents an overview of "Retrieval-Augmented Generation for Large Language Models: A Survey" (2023), a comprehensive survey on RAG hosted by BAAI's simg repository. The post situates the work at the intersection of retrieval-augmented generation and large-scale search/recommendation systems, where efficiency, scalability, and intent understanding remain core challenges. It organizes the field around a taxonomy covering modeling paradigms (discriminative vs. generative retrieval, e.g., dual-tower encoders, cross-encoders, DSI), LLM integration patterns (RAG, agents, tool use), optimization objectives, and evaluation protocols (nDCG, MRR, LLM-as-judge). Four technical lines are contrasted: dense retrieval, late interaction (e.g., ColBERT), generative IR, and agentic search. The post also traces the field's evolution from BERT reranking and DPR (2019-2021) through RAG-era fusion (2022-2023) to agentic search, Deep Research, and GraphRAG (2024+), and highlights open problems including evaluation reliability, latency and cost, hallucination, safety, and cross-lingual/multimodal extension. An engineering checklist for production RAG deployment is included.

Retrieval-Augmented Generation for Large Language Models: A Survey (2023)

This post summarizes a 2023 survey, "Retrieval-Augmented Generation for Large Language Models: A Survey", available via the BAAI simg paper repository:

https://simg.baai.ac.cn/paperfile/25a43194-c74c-4cd3-b60f-0a1f27f8b8af.pdf

Key points

  • The survey addresses RAG challenges in large-scale search, recommendation, and personalization systems: efficiency, scalability, and user-intent understanding. 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.
  • It provides a unified perspective that brings scattered related work into a comparable framework, decomposing methods into components such as representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms.
  • It discusses interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, and outlines the path from research prototypes to industrial systems.
  • Taxonomy

    | Dimension | Subcategories | Representative ideas | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Dual-tower, cross-encoders, 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 | Scarce annotations | | Evaluation | Offline / online / human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Diverges from real satisfaction |

    Four technical lines

  • 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 via tokens or docids, simplifying cascades.
  • Agentic search: models search as sequential decision-making, supporting multi-hop reasoning and self-reflection.
  • Timeline of the field

  • 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 surge.
  • 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth areas.
  • Evaluation and benchmarks

    Typical datasets and metrics covered include:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain corpora, public recommendation sets.
  • 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.
  • Note: concrete numeric results should be verified against the original PDF.

    Main takeaways

    1. Architecture: cascaded retrieval + rerank + generation remains mainstream, but the agentic paradigm makes "when and how many times to retrieve" itself learnable. 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data risks knowledge leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human evaluation. 4. Production: latency, cost, explainability, and safety are hard constraints — do not optimize only academic benchmarks.

    Open problems

  • Insufficient unified benchmarks; non-reproducible private data.
  • LLM evaluation bias.
  • Safety and cost constraints of agentic systems on the open web.
  • Future directions: finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, multimodal and cross-lingual consistency.
  • Engineering checklist

    | Item | Question | Suggestion | |---|---|---| | Data | PII in training/index? Version management? | Partitioned indexes, anonymization, rollback-capable embedding versions | | Latency | p99 budget? How many retrieval steps? | Cascade + early stopping, caching hot queries, async reranking | | Quality | Do offline gains transfer to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelisting, adversarial detection, output filtering | | Cost | Token and GPU usage per query? | Small-model routing, distillation, hybrid sparse+dense |

    Glossary

  • 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 invocation
  • Gen-IR: Generative Information Retrieval
  • Related entries

  • A Comprehensive Survey on Reinforcement Learning-based Agentic Search (arXiv:2510.16724)
  • A Survey of Conversational Search, Oct 2024 (arXiv:2410.15576)
  • A Survey of LLM-Empowered Agents for Recommendation (arXiv:2503.05659)
  • A Survey of Model Architectures in Information Retrieval, Jan 2025 (arXiv:2502.14822)
  • A Survey on AI Search with Large Language Models, July 2025
  • A Survey on Knowledge-Oriented Retrieval-Augmented Generation, Mar 2025 (arXiv:2503.10677)

Tags

#rag#retrieval-augmented-generation#large-language-models#information-retrieval#survey#agentic-search#dense-retrieval#llm-evaluation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208978