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

SIGIR 2024 Workshop on eCommerce (ECOM24)

Forum topic · 小凯 · 2026-07-05

Summary

This entry catalogs the SIGIR 2024 Workshop on eCommerce (ECOM24), a workshop held in conjunction with the SIGIR 2024 conference focused on information retrieval challenges in large-scale e-commerce systems. The workshop covers topics at the intersection of search, recommendation, and personalization, including retrieval and ranking pipelines, user intent understanding, conversational and semantic search, and the integration of large language models (LLMs) into e-commerce search and recommendation stacks. The source page serves as an index entry within a curated list of conferences and workshops, linking to the official publication record on the ACM Digital Library (DOI: 10.1145/3626772.3657988) and cross-referencing related events such as the 2025 SIGIR Workshop on eCommerce, CIKM 2024 Workshop on Multimodal Search and Recommendations, and EACL 2024 Workshop on Personalization of Generative AI Systems. Detailed program specifics are not reproduced on the source page; readers should consult the linked ACM record and the workshop's official site for accepted papers, schedules, and organizers.

SIGIR 2024 Workshop on eCommerce (ECOM24)

Overview

The SIGIR 2024 Workshop on eCommerce (ECOM24) is a workshop co-located with the SIGIR 2024 conference. It focuses on information retrieval research applied to e-commerce, where large-scale search, recommendation, and personalization systems face persistent challenges around efficiency, scalability, and user intent understanding.

| Field | Content | |-------|---------| | Title | SIGIR 2024 Workshop on eCommerce (ECOM24) | | Type | Conference / Workshop | | Link | https://dl.acm.org/doi/10.1145/3626772.3657988 | | Section | Conferences, Workshops |

Topic Scope

E-commerce search and recommendation systems traditionally split retrieval, ranking, and generation into separate pipeline stages. In the LLM era, users increasingly expect natural-language interaction, multi-hop reasoning, and up-to-date knowledge, which stresses these pipelines. Workshops in this space typically address:

  • Open-domain information access and enterprise/product knowledge retrieval
  • Conversational search and semantic understanding in recommendation
  • End-to-end architectures combining external knowledge sources with generative models
  • Interfaces with LLM tool calling, reinforcement learning, and multi-agent collaboration
  • Open problems such as evaluation credibility, latency and cost, hallucination and safety, and cross-lingual / multimodal extension
  • *Note: the source page is an index entry and does not reproduce the full call for papers or accepted-paper list; the specifics above reflect the typical scope of this workshop series.*

    Context in the SIGIR / RecSys Ecosystem

    Neural information retrieval has evolved from BM25 through BERT cross-encoders, dense bi-encoder retrieval, and late interaction, toward generative retrieval and LLM-based agents. Each generation trades off efficiency, effectiveness, and maintainability. On the recommendation side, the field has moved from matrix factorization and deep CTR models to sequence Transformers and LLM-driven generative recommendation (Gen-Rec), contending with sparse user behavior, massive item catalogs, and multi-objective business goals.

    RAG and agentic search extend external knowledge access from one-shot retrieval to iterative, verifiable, plannable processes — shifting evaluation from static nDCG toward task success rate, citation accuracy, and multi-hop reasoning-chain completeness.

    Practical Takeaways for Practitioners

    1. Architecture: cascaded retrieval + reranking + generation remains mainstream, but agentic paradigms treat retrieval count and strategy itself as learnable. 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data requires safeguards against knowledge leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction keeps widening; LLM-as-judge should be cross-validated with human evaluation. 4. Deployment: latency, cost, explainability, and safety are hard production constraints — do not optimize academic benchmarks alone.

    Engineering Checklist

    | Check | Question | Suggestion | |-------|----------|------------| | Data | Does training/index data contain PII? How are versions managed? | Partitioned indexes, anonymization, rollback-able embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascades with 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 cost? | Small-model routing, distillation, hybrid sparse+dense retrieval |

    Related Entries

  • 2025 SIGIR Workshop on eCommerce
  • CIKM 2024 1st Workshop on Multimodal Search and Recommendations
  • EACL 2024 Workshop on Personalization of Generative AI Systems
  • ICDM MMSR 2025
  • References

  • Official record: ACM DL — https://dl.acm.org/doi/10.1145/3626772.3657988
  • For organizers, accepted papers, and schedule, consult the workshop's official website and the linked ACM record.

Tags

#sigir-2024#ecommerce#workshop#information-retrieval#recommendation-systems#search#llm#conferences

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/178208501