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

How Can Recommender Systems Benefit from Large Language Models: A Survey (ACM TOIS 2025)

Forum topic · 小凯 · 2026-07-05

Summary

This survey, published in ACM Transactions on Information Systems (2025), systematically examines how large language models (LLMs) can enhance recommender systems. It organizes existing work into a unified taxonomy covering modeling paradigms (discriminative vs. generative retrieval), LLM integration patterns (RAG, agents, tool use), optimization objectives (relevance, diversity, freshness), and evaluation protocols (offline metrics, online A/B tests, LLM-as-judge). The paper traces the field's evolution from neural ranking and dense retrieval to generative recommendation (Gen-RecSys) and agentic, LLM-powered pipelines, and discusses interfaces with reinforcement learning and multi-agent collaboration. It also identifies open challenges including evaluation trustworthiness, latency and cost constraints, hallucination and safety risks, and cross-lingual and multimodal generalization. The survey serves as a practical reference for researchers and engineers building LLM-augmented recommendation pipelines, offering a comparison of representative approaches and a checklist for industrial deployment. Source: https://dl.acm.org/doi/abs/10.1145/3678004

How Can Recommender Systems Benefit from Large Language Models: A Survey (ACM TOIS 2025)

This post introduces the survey "How Can Recommender Systems Benefit from Large Language Models: A Survey", published in *ACM Transactions on Information Systems* (2025).

  • Source: https://dl.acm.org/doi/abs/10.1145/3678004
  • Type: Survey
  • Background and Motivation

    Traditional recommender pipelines separate retrieval, ranking, and generation, which limits their ability to meet modern user expectations for natural-language interaction, multi-hop reasoning, and up-to-date knowledge. This survey systematically maps how LLMs can be applied across the recommendation stack, covering open-domain information access, conversational search, semantic understanding in recommendation, and end-to-end architectures that combine external knowledge sources with generative models.

    Core Contributions

  • A unified perspective that organizes scattered related work into a comparable framework.
  • A clear decomposition of method components: representation learning, retrievers, re-rankers, planners, generators, and feedback mechanisms.
  • Reproducible benchmarks, datasets, and taxonomy tables that lower the entry barrier for new researchers.
  • Discussion of interfaces with LLM tool use, reinforcement learning, and multi-agent collaboration, including paths from research prototypes to production systems.
  • Explicit open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual/multimodal extension.
  • Taxonomy

    | Dimension | Subcategory | 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 annotations | | Evaluation | Offline / Online / Human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Divergence from real satisfaction |

    Research Evolution

  • 2019–2021: BERT re-ranking and DPR establish neural retrieval foundations.
  • 2022–2023: RAG and FreshLLMs drive retrieval-generation fusion.
  • 2024 onward: Conversational/agentic search and Gen-RecSys proliferate.
  • 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth fronts.
  • Evaluation Landscape

    Common benchmarks and metrics covered by the survey 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, token cost.
  • Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs.
  • Quantitative results should be verified against the original PDF.

    Key Insights

    1. Architecture: Cascaded retrieval + re-ranking + 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 knowledge leakage and distribution shift. 3. Evaluation: The gap between offline metrics and online satisfaction is widening; LLM-as-judge requires cross-validation with human assessment. 4. Production: Latency, cost, interpretability, and safety are hard constraints—academic benchmarks alone are insufficient.

    Limitations and Future Directions

    Identified gaps include insufficient unified benchmarks, non-reproducible private data, LLM evaluation bias, and safety/cost constraints for agentic systems. Future work includes finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, and multimodal/cross-lingual consistency, as well as causal and fairness constraints for recommenders.

    Related Reading

  • A Comprehensive Review on Harnessing Large Language Models to Overcome…
  • A Comprehensive Survey on Cross-Domain Recommendation
  • A Comprehensive Survey on Retrieval Methods in Recommender Systems
  • A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
  • A Survey of Generative Search and Recommendation in the Era of Large Language Models
  • A Survey on LLM-powered Agents for Recommender Systems

Tags

#recommender-systems#large-language-models#survey#rag#acm-tois#generative-retrieval#agentic-search#information-retrieval

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/178208900