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

LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models (ACM TOIS 2025)

Forum topic · 小凯 · 2026-07-05

Summary

LLMCDSR is a research paper published in ACM Transactions on Information Systems (2025) that explores using Large Language Models (LLMs) to enhance cross-domain sequential recommendation. The work addresses long-standing challenges in recommendation systems, including efficiency, scalability, and user intent understanding, particularly where traditional pipelines separate retrieval, ranking, and generation stages. The paper situates itself at the intersection of sequential recommendation and LLM-era capabilities such as natural language interaction, multi-hop reasoning, and semantic priors that can help with sparse user behavior and cold-start scenarios. The forum post frames the contribution within the broader evolution from matrix factorization and deep CTR models to sequential Transformers and generative recommendation (Gen-Rec), and discusses how LLMs shift the boundaries between retrieval, ranking, generation, and tool calling. Key discussion points include cascaded retrieve-rank-generate architectures, evaluation credibility, latency and cost constraints, hallucination risks, and the gap between offline metrics and online satisfaction. The post links to the official ACM Digital Library page (DOI: 10.1145/3715099) and cross-references related work such as BERT4Rec, Mamba4Rec, EAGER, and P5. Readers should consult the original PDF for quantitative results.

LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models (ACM TOIS 2025)

Overview

| Field | Content | |---|---| | Title | LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models | | Venue | ACM Transactions on Information Systems (TOIS), 2025 | | Source | https://dl.acm.org/doi/abs/10.1145/3715099 | | Category | Sequential Recommendation |

Key points

  • LLMCDSR applies Large Language Models to cross-domain sequential recommendation, aiming to improve user intent understanding, efficiency, and scalability in large-scale personalized systems.
  • The work responds to the limits of traditional pipelines that treat retrieval, ranking, and generation as disconnected stages, and to new expectations in the LLM era: natural language interaction, multi-hop reasoning, and up-to-date knowledge.
  • It leverages the semantic priors and cold-start capabilities of LLMs, while acknowledging that online inference cost and hallucination risk require careful system design.
  • Context in the field

    The post situates the paper within the evolution of recommendation and information retrieval:

    1. IR side: from BM25 → BERT cross-encoders → dual-tower dense retrieval → late interaction → generative retrieval and LLM agents. Each generation balances an efficiency–effectiveness–maintainability triangle. 2. Recommendation side: from matrix factorization and deep CTR models → sequential Transformers → LLM instruction-following and generative recommendation (Gen-Rec). Core tensions: sparse user behavior, huge item catalogs, and multi-objective business trade-offs. 3. LLM-era shift: retrieval becomes iterative, verifiable, and plannable (RAG / agentic search); the new variables are inference budget and action space (whether to retrieve, how many steps, which tools to call).

    Architecture discussion

    The general technical pipeline described follows four stages:

    1. Input and representation — encoding queries, documents, and user context into dense/sparse representations or structured prompts; 2. Core modules — retrievers, rerankers, planners, memory modules, and tool interfaces, composed in series or parallel; 3. Learning strategy — supervised fine-tuning, contrastive learning, distillation, reinforcement learning, and synthetic data bootstrapping; 4. Inference strategy — single-pass vs. iterative retrieval, parallel sub-queries, early stopping, and budget control.

    Evaluation considerations

    Typical benchmarks and metrics in this area include MS MARCO, BEIR, Natural Questions, and public recommendation datasets; metrics include nDCG@10, MRR, Recall@k, Hit@k, task success rate, latency, and token cost. Baselines usually cover BM25, dense retrieval, cross-encoder reranking, and retrieval-free LLMs.

    > Note: The exact quantitative results of LLMCDSR should be verified against the original PDF. This post is based on the abstract and public metadata.

    Takeaways for search/rec practitioners

    1. Architecture: cascaded retrieve–rerank–generate remains mainstream, but agentic paradigms make retrieval strategy itself learnable. 2. Data: high-quality instruction data and click/session logs matter equally; 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 assessment. 4. Production: latency, cost, explainability, and safety are hard constraints — optimizing academic benchmarks alone is insufficient.

    Related entries

  • BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations
  • EAGER: Two-Stream Generative Recommender
  • Efficient On-Device Session-Based Recommendation
  • How to Index Item IDs for Recommendation Foundation Models (P5)
  • Mamba4Rec: Efficient Sequential Recommendation with Selective State Space Models (arXiv:2403.03900)
  • References

  • Original paper: LLMCDSR — ACM Digital Library

Tags

#recommendation-systems#large-language-models#sequential-recommendation#cross-domain-recommendation#information-retrieval#acm-tois#rag#gen-rec

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/178208989