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

Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains

Forum topic · 小凯 · 2026-07-05

Summary

This forum post introduces an arXiv paper (2502.09089, February/March 2025) describing how Walmart eCommerce builds semantic ads retrieval using language models progressively trained on multiple knowledge domains. The work addresses a core challenge in large-scale search, recommendation, and personalization systems: efficiently understanding user intent while balancing retrieval quality, latency, and scalability. The paper proposes progressively training language models across multiple knowledge domains so that the models acquire both general semantic understanding and domain-specific knowledge relevant to e-commerce advertising, enabling better matching between user queries and sponsored products. The forum entry situates the paper within the broader evolution of neural information retrieval, from BM25 and dense bi-encoders to cross-encoder rerankers, generative retrieval, and LLM-based agentic search. It also discusses engineering considerations for production deployment, including latency budgets, embedding index versioning, offline-versus-online metric gaps, safety concerns such as index poisoning, and per-query token costs. Authors include Zhaodong Wang, Weizhi Du, Md Omar Faruk Rokon, Pooshpendu Adhikary, Yanbing Xue, and Jiaxuan Xu, among nine contributors from Walmart.

Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains

This post summarizes an arXiv paper on semantic ads retrieval deployed in the context of Walmart eCommerce, using language models progressively trained on multiple knowledge domains.

Paper metadata

  • Title: Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains
  • Authors: Zhaodong Wang, Weizhi Du, Md Omar Faruk Rokon, Pooshpendu Adhikary, Yanbing Xue, Jiaxuan Xu, et al. (9 authors in total)
  • Published: March 2025 (arXiv, listed as 2502.09089)
  • Source: https://arxiv.org/abs/2502.09089
  • Category: Verticals / Industrial IR
  • One-line summary

    The paper presents Walmart's approach to semantic ads retrieval, where language models are progressively trained across multiple knowledge domains to improve query–ad understanding at eCommerce scale.

    Background and motivation

    In large-scale search, recommendation, and personalization systems, information retrieval has long faced challenges around efficiency, scalability, and user intent understanding. Traditional pipelines often separate retrieval, ranking, and generation, which struggles to meet the combined demands of natural language interaction, multi-hop reasoning, and up-to-date knowledge in the LLM era. This paper is situated in that context, targeting the ads retrieval vertical of eCommerce search.

    Context within neural IR

    The post situates the work within the broader evolution of neural information retrieval:

  • From BM25 to BERT cross-encoders, dense bi-encoder retrieval, late interaction, and finally generative retrieval and LLM-based agentic search.
  • Dense retrieval enables millisecond-level recall via approximate nearest neighbor search but is sensitive to domain shift and long-tail queries.
  • Cross-encoders offer high precision but cannot precompute document representations.
  • Generative approaches reduce cascade errors but face index-update difficulties.
  • For recommendation, the core tensions remain sparse user behavior, massive item catalogs, and multi-objective business trade-offs. LLMs provide semantic priors and cold-start capability, but online inference cost and hallucination risk demand careful system design.

    Engineering checklist for production deployment

    | Aspect | Question | Suggestion | |--------|----------|------------| | Data | Does training/indexing contain PII? How are versions managed? | Partitioned indexes, anonymization, rollback-safe embedding versions | | Latency | What is the p99 budget? How many retrieval hops? | Cascaded retrieval + early stopping, caching popular queries, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, manual audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelists, adversarial detection, output filtering | | Cost | Token and GPU cost per query? | Route to smaller models, distillation, hybrid sparse+dense retrieval |

    Takeaways for readers

    1. Researchers: Reproduce the core comparisons; check whether the paper reports statistical significance and compute costs. 2. Engineers: Extract pluggable modules (encoder, reranker, planner) and evaluate integration costs against existing stacks. 3. Product managers: Focus on user-perceivable benefits — latency, answer trustworthiness, multi-turn consistency — rather than offline nDCG alone.

    Related entries

  • An interpretable ensemble of graph and language models for improving search
  • Applying Deep Learning to Ads Conversion Prediction in Last Mile Delivery (arXiv 2502.10514)
  • Automated Query-Product Relevance Labeling using Large Language Models (arXiv 2502.15990)
  • Behavior Modeling Space Reconstruction for E-Commerce Search (arXiv 2501.18216)
  • Behavior-driven query similarity prediction based on pre-trained language models
  • Better to Ask in English: Cross-Lingual Evaluation of Large Language Models (DOI: 10.1145/3589334.3645643)
> Note: Quantitative results should be verified against the original PDF; this summary is based on the abstract and public metadata.

Tags

#semantic-retrieval#ecommerce-search#advertising#language-models#information-retrieval#walmart#arxiv#industrial-ir

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/178209038