Recommender Systems in the Era of Large Language Models (LLMs) — TKDE Survey (Nov 2024)
Overview
| Field | Details | |-------|---------| | Title | Recommender Systems in the Era of Large Language Models (LLMs) | | Venue | IEEE Transactions on Knowledge and Data Engineering (TKDE), November 2024 | | Access | By subscription | | Source | https://ieeexplore.ieee.org/document/10506571 | | Type | Academic survey paper | | Section | Recommender Engine Surveys |
Background and Motivation
Recommendation systems have long faced challenges in efficiency, scalability, and user intent understanding. Traditional pipeline approaches often separate retrieval, ranking, and generation, making it difficult to meet users' combined needs in the LLM era for natural language interaction, multi-hop reasoning, and real-time knowledge. This TKDE survey was written against this backdrop, aiming to systematically map the theory and practice at the intersection of large language models and recommender systems.
Core Contributions
- Provides a unified perspective that brings scattered related work into a comparable framework.
- Gives a clear decomposition of method components — representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms — to facilitate engineering adoption.
- Offers reproducible benchmarks, datasets, and taxonomy tables through its survey coverage, lowering the entry barrier for subsequent researchers.
- Discusses interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, outlining paths from research prototypes to industrial systems.
- Explicitly lists open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual/multimodal extension.
- A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System 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-Rec) (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)
- Original paper: Recommender Systems in the Era of Large Language Models (LLMs), TKDE, Nov 2024 — https://ieeexplore.ieee.org/document/10506571 (subscription required)
Technical Positioning
The work sits at the intersection of recommendation and large-scale search/recommendation systems. From a systems perspective, it addresses the core question of how to redraw the responsibility boundaries among retrieval, ranking, generation, and tool calling in the LLM era. New variables introduced by LLMs include the reasoning budget and the action space (whether to retrieve, how many times, and which tools to invoke).
Neural information retrieval has evolved from BM25 through BERT cross-encoders, bi-encoder dense retrieval, and late interaction, to generative retrieval and LLM agents — each generation balancing efficiency, effectiveness, and maintainability. On the recommendation side, the field has moved from matrix factorization and deep CTR models to sequential Transformers and LLM-driven generative recommendation (Gen-Rec). LLMs offer semantic priors and cold-start capability, but online inference cost and hallucination risk demand careful system design.
Engineering Considerations
| Concern | Question | Suggestion | |---------|----------|------------| | Data | PII in training/index data? Versioning? | Partitioned indexes, anonymization, rollback-capable embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascade + early stopping, caching hot queries, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source allowlists, adversarial detection, output filtering | | Cost | Per-query token and GPU usage? | Route to smaller models, distillation, hybrid sparse+dense retrieval |
Limitations and Future Directions
Likely limitations include experiment scale constrained by GPU budgets, mismatch between benchmarks and real user distributions, English-centric data with unknown cross-lingual generalization, and safety risks of agent systems on the open web. Future directions include more efficient test-time compute allocation, deeper integration with knowledge graphs and structured databases, and causal/fairness constraints for recommender systems.