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

Leveraging Large Language Models for Sequential Recommendation (RecSys 2023)

Forum topic · 小凯 · 2026-07-05

Summary

This RecSys 2023 paper, 'Leveraging Large Language Models for Sequential Recommendation' (DOI: 10.1145/3604915.3610639), explores how large language models can enhance sequential recommendation systems. Traditional pipelines separate retrieval, ranking, and generation, which limits their ability to model user intent in the LLM era. The work positions LLMs as semantic encoders or recommendation backbones that can leverage open-world knowledge, natural language understanding, and reasoning to improve next-item prediction, particularly for cold-start users and sparse interaction data. The article summarizes the paper's motivation, methodological components (representations, retrievers, rerankers, generators, and feedback mechanisms), evaluation protocols, and open challenges such as inference latency, cost, hallucination, and evaluation trustworthiness. It also provides engineering insights on integrating LLM-based recommendation modules into production systems, including latency budgets, data privacy, and safety considerations. Readers are directed to the ACM Digital Library for the full text and quantitative results.

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.
  • 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

  • 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.
  • 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.

    Related Entries

  • 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
  • References

  • Original paper: Leveraging Large Language Models for Sequential Recommendation, RecSys 2023. https://dl.acm.org/doi/abs/10.1145/3604915.3610639

Tags

#large-language-models#sequential-recommendation#recsys-2023#recommender-systems#llm#information-retrieval#personalization

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/178208917