Leveraging Large Language Models for Sequential Recommendation (RecSys 2023)
Overview
This post introduces a RecSys 2023 paper: Leveraging Large Language Models for Sequential Recommendation.
| Field | Content | |------|------| | Title | Leveraging Large Language Models for Sequential Recommendation, RecSys 2023 | | Venue | RecSys 2023 | | Link | https://dl.acm.org/doi/abs/10.1145/3604915.3610639 | | Type | Academic paper | | Categories | Recommender Engines, Sequential Recommendation |
Background and Motivation
Sequential recommendation has long faced challenges around scalability, efficiency, and understanding user intent. Traditional pipelines separate retrieval, ranking, and generation, making it hard to meet modern expectations for natural language interaction, multi-hop reasoning, and up-to-date knowledge in the LLM era. This paper addresses that gap by examining how large language models can be applied to sequential recommendation.
Core Contributions
- A unified perspective on combining LLMs with sequential recommendation, bringing scattered related work into a comparable framework.
- A clear decomposition of method components (representation learning, retrievers, rerankers, planners, generators, feedback mechanisms) for engineering practice.
- Discussion of interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration.
- Identification of open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual / multimodal extension.
- 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 reranking, retrieval-free LLMs, commercial search APIs.
- 360Brew: A Decoder-only Foundation Model for Personalized Ranking and …
- Actions Speak Louder than Words: Trillion-Parameter Sequential Transdu…
- Augmenting Netflix Search with In-Session Adapted Recommendations, Rec…
- Bridging Language and Items for Retrieval and Recommendation, Mar 2024…
- Data-efficient Fine-tuning for LLM-based Recommendation, SIGIR 2024
- DiffKG: Knowledge Graph Diffusion Model for Recommendation, WSDM 2024
- Original paper: Leveraging Large Language Models for Sequential Recommendation, RecSys 2023. https://dl.acm.org/doi/abs/10.1145/3604915.3610639
Typical Method Pipeline
1. Input and representation: encode queries, items, and user context as dense/sparse representations or structured prompts; 2. Core modules: retrievers, rerankers, planners, memory modules, and tool interfaces composed in series or parallel; 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, RL (including process rewards), and synthetic data; 4. Inference strategies: single-pass retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control.
Evaluation Considerations
For exact numerical results, please refer to the original PDF via the DOI link above.
Key Takeaways
1. Architecture: cascaded retrieval + reranking + generation remains mainstream, but agentic paradigms treat retrieval frequency and strategy itself as learnable; 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data must guard against 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. Deployment: latency, cost, explainability, and safety are hard constraints in production—do not optimize academic benchmarks alone.