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

A Survey on Large Language Models for Recommendation (WWW 2024, Springer)

Forum topic · 小凯 · 2026-07-05

Summary

This survey, published at WWW 2024 and available via Springer (DOI: 10.1007/s11280-024-01291-2), systematically reviews the integration of large language models (LLMs) into recommender systems. It organizes the rapidly growing literature into a comparable taxonomy covering modeling paradigms (discriminative vs. generative retrieval, LLM-based ranking), LLM integration patterns (retrieval-augmented generation, agents, tool use), optimization objectives (relevance, diversity, freshness), and evaluation protocols (offline metrics, online A/B tests, LLM-as-judge). The survey traces the field's evolution from neural retrieval foundations (BERT re-ranking, dense retrieval) through retrieval-generation fusion to current generative recommendation (Gen-RecSys) and agentic paradigms. It contrasts representative lines of work, including dense retrieval, late-interaction models like ColBERT, generative IR, and agentic search that models retrieval as sequential decision-making. Key open problems identified include benchmark inconsistency, evaluation reliability, latency and cost constraints, hallucination and safety risks, and cross-lingual/multimodal generalization. The article is a useful reference for researchers and engineers building LLM-powered recommendation pipelines, offering a structured view of method components, benchmarks, and the gap between academic results and production constraints.

A Survey on Large Language Models for Recommendation (WWW 2024, Springer)

Overview

This survey, published at WWW 2024 and hosted by Springer, systematically reviews research on applying large language models (LLMs) to recommender systems.

  • Title: A survey on large language models for recommendation
  • Venue: WWW 2024 / Springer (World Wide Web journal)
  • Link: https://link.springer.com/article/10.1007/s11280-024-01291-2
  • Type: Survey
  • Background and Motivation

    Traditional recommendation pipelines separate retrieval, ranking, and generation stages, which limits adaptability to the LLM era's demands for natural-language interaction, multi-hop reasoning, and up-to-date knowledge. This survey positions itself at the intersection of large-scale search, recommendation, and personalization, addressing how responsibilities among retrieval, ranking, generation, and tool invocation should be redistributed when LLMs enter the stack.

    Key Points

  • Unified perspective: consolidates scattered LLM-for-recommendation work into a comparable framework.
  • Component decomposition: clearly separates representations, retrievers, re-rankers, planners, generators, and feedback mechanisms for engineering practice.
  • Taxonomy and benchmarks: provides reproducible classification tables and protocol coverage that lower the entry barrier for new researchers.
  • Interfaces to emerging paradigms: discusses connections to LLM tool calling, reinforcement learning, and multi-agent collaboration, plus paths from research prototypes to industrial systems.
  • Open problems: evaluation trustworthiness, latency and cost, hallucination and safety, cross-lingual and multimodal extension.
  • Taxonomy

    | Dimension | Subclasses | Representative Ideas | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Two-tower, cross-encoders, DSI, GPT-indexed | 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 annotation | | Evaluation | Offline / online / human | nDCG, MRR, LLM-as-judge, A/B | Comparable | Deviates from real satisfaction |

    Evolution of the Field

  • 2019–2021: BERT re-ranking and dense passage retrieval (DPR) establish neural retrieval foundations.
  • 2022–2023: RAG and FreshLLM drive retrieval-generation fusion.
  • 2024 onwards: Conversational/agentic search and generative recommender systems (Gen-RecSys) surge.
  • 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth areas.
  • Four main methodological lines are typically compared:

  • Dense retrieval: high recall, low latency; suited to 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.
  • Evaluation Paradigms

    Common benchmarks and metrics covered in surveys of this area include:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain corpora, public recommendation datasets.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency and token cost.
  • Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs.
  • Ablations: contributions of retrieval steps, re-ranking depth, and training data scale.
  • Exact quantitative results should be verified against the original PDF tables.

    Insights and Implications

    1. Architecture: cascaded retrieval + re-ranking + 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 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, interpretability, and safety are hard constraints in industrial deployment—academic benchmarks alone are insufficient.

    Limitations and Future Directions

    Commonly noted limitations include insufficient unified benchmarks, non-reproducible private data, LLM evaluation bias, and safety/cost constraints of agentic systems. Future work covers finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, and multimodal/cross-lingual consistency, as well as efficient test-time compute allocation, deeper fusion with knowledge graphs and structured databases, and causal/fairness constraints for recommendation.

    Related Entries

  • A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender Systems Challenges (arXiv 2507.21117)
  • A Comprehensive Survey on Cross-Domain Recommendation (arXiv 2503.14110)
  • A Comprehensive Survey on Retrieval Methods in Recommender Systems (arXiv 2407.21022)
  • A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys, DOI 10.1145/3637528.3671474)
  • A Survey of Generative Search and Recommendation in the Era of Large Language Models (arXiv 2404.16924)
  • A Survey on LLM-powered Agents for Recommender Systems (arXiv 2502.10050)

Tags

#large-language-models#recommender-systems#survey#generative-recommendation#retrieval-augmented-generation#information-retrieval#www-2024#agentic-search

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/178208911