Unified Supervision for Walmart's Sponsored Search Retrieval via Joint Semantic Relevance and Behavioral Engagement Modeling

• URL: http://arxiv.org/abs/2604.07930v3
• Date: Wed, 15 Apr 2026 05:40:56 GMT
• Title: Unified Supervision for Walmart's Sponsored Search Retrieval via Joint Semantic Relevance and Behavioral Engagement Modeling
• Abstract summary: We propose a bi-encoder training framework for Walmart's sponsored search retrieval in e-commerce.<n>We use semantic relevance as the primary supervision signal, with engagement used only as a preference signal among relevant items.<n>Our approach outperforms the current production system in both offline evaluation and online AB tests.
• Score: 5.167327964319347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern search systems rely on a fast first stage retriever to fetch relevant items from a massive catalog of items. Deployed search systems often use user engagement signals to supervise bi-encoder retriever training at scale, because these signals are continuously logged from real traffic and require no additional annotation effort. However, engagement is an imperfect proxy for semantic relevance. Items may receive interactions due to popularity, promotion, attractive visuals, titles, or price, despite weak query-item relevance. These limitations are further accentuated in Walmart's e-commerce sponsored search. User engagement on ad items is often structurally sparse because the frequency with which an ad is shown depends on factors beyond relevance such as whether the advertiser is currently running that ad, the outcome of the auction for available ad slots, bid competitiveness, and advertiser budget. Thus, even highly relevant query ad pairs can have limited engagement signals simply due to limited impressions. We propose a bi-encoder training framework for Walmart's sponsored search retrieval in e-commerce that uses semantic relevance as the primary supervision signal, with engagement used only as a preference signal among relevant items. Concretely, we construct a context-rich training target by combining 1. graded relevance labels from a cascade of cross-encoder teacher models, 2. a multichannel retrieval prior score derived from the rank positions and cross-channel agreement of retrieval systems running in production, and 3. user engagement applied only to semantically relevant items to refine preferences. Our approach outperforms the current production system in both offline evaluation and online AB tests, yielding consistent gains in average relevance and NDCG.

Related papers

• Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce [33.55727546262202]
  CaLIR is a category-guided latent intent reasoning framework for e-commerce generative retrieval.<n>We introduce hierarchical semantic reasoning to align latent states with category-level shopping intent.<n>Experiments on multilingual e-commerce search datasets show that CaLIR achieves a better balance between retrieval effectiveness and inference efficiency than existing methods.
  arXiv  Detail & Related papers  (2026-06-05T09:12:54Z)
• LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots [38.35931897144688]
  We propose LERA, a two-stage retrieve-then-generate auction framework for large language model (LLM)-based chatbots.<n>In the first stage, embedding-based coarse filtering pre-selects a small set of candidate advertisers.<n>In the second stage, the LLM itself is queried with a carefully designed prompt to produce logits over candidates, which serve as refined organic relevance scores.
  arXiv  Detail & Related papers  (2026-05-15T15:39:30Z)
• CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search [51.911048955965136]
  CoSearch is a framework that jointly trains a multi-step reasoning agent and a generative document ranking model.<n>Our results show that joint training of the reasoning agent and retrieval system is both feasible and strongly performant.
  arXiv  Detail & Related papers  (2026-04-19T17:48:17Z)
• One Model, Two Markets: Bid-Aware Generative Recommendation [7.863030229448138]
  We propose a unified framework that integrates commercial relevance and monetization objectives directly into the generative sequence.<n>We introduce control tokens to decouple the decision of whether to show an ad from which item to show.<n>We also devise a Bid-Aware Decoding mechanism that handles real-time pricing, injecting bids directly into the inference process to steer the generation toward high-value items.
  arXiv  Detail & Related papers  (2026-03-23T17:27:59Z)
• Practice on Long Behavior Sequence Modeling in Tencent Advertising [75.65309022911994]
  Long-sequence modeling has become an indispensable frontier in recommendation systems for capturing users' long-term preferences.<n>We propose several practical approaches within the two-stage framework for long-sequence modeling.<n> Deployed in production on Tencent's large-scale advertising platforms, our innovations delivered significant performance gains.
  arXiv  Detail & Related papers  (2025-09-10T06:55:57Z)
• Bidding-Aware Retrieval for Multi-Stage Consistency in Online Advertising [30.108437268612438]
  Bidding-Aware Retrieval (BAR) is a model-based retrieval framework that addresses multi-stage inconsistency by incorporating ad bid value into the retrieval scoring function.<n>BAR's core innovation is Bidding-Aware Modeling, incorporating bid signals through monotonicity-constrained learning and multi-task distillation to ensure economically coherent representations.<n>Extensive offline experiments and full-scale deployment across Alibaba's display advertising platform validated BAR's efficacy.
  arXiv  Detail & Related papers  (2025-08-07T09:43:34Z)
• EgoPrompt: Prompt Learning for Egocentric Action Recognition [49.12318087940015]
  EgoPrompt is a prompt learning-based framework to conduct egocentric action recognition task.<n>EgoPrompt achieves state-of-the-art performance across within-dataset, cross-dataset, and base-to-novel generalization benchmarks.
  arXiv  Detail & Related papers  (2025-08-05T09:47:07Z)
• HCMRM: A High-Consistency Multimodal Relevance Model for Search Ads [10.61722566941537]
  This paper focuses on improving query-to-video relevance matching to enhance the effectiveness of ranking in ad systems.<n>It utilizes a simple yet effective method to enhance the consistency between pre-training and relevance tasks.<n>The proposed method has been deployed in the Kuaishou search advertising system for over a year, contributing to a 6.1% reduction in the proportion of irrelevant ads and a 1.4% increase in ad revenue.
  arXiv  Detail & Related papers  (2025-02-09T09:07:11Z)
• Middleman Bias in Advertising: Aligning Relevance of Keyphrase Recommendations with Search [4.275764895529604]
  We describe the shortcomings of training relevance filter models on biased click/sales signals.<n>We re-conceptualize advertiser keyphrase relevance as interaction between two dynamical systems.<n>We discuss the bias of search relevance systems and the need to align advertiser keyphrases with search relevance signals.
  arXiv  Detail & Related papers  (2025-01-31T19:28:26Z)
• ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
  This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries. We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
  arXiv  Detail & Related papers  (2022-07-14T17:46:37Z)
• Incentives for Item Duplication under Fair Ranking Policies [69.14168955766847]
  We study the behaviour of different fair ranking policies in the presence of duplicates. We find that fairness-aware ranking policies may conflict with diversity, due to their potential to incentivize duplication more than policies solely focused on relevance.
  arXiv  Detail & Related papers  (2021-10-29T11:11:15Z)
• Compositional Attention: Disentangling Search and Retrieval [66.7108739597771]
  Multi-head, key-value attention is the backbone of the Transformer model and its variants. Standard attention heads learn a rigid mapping between search and retrieval. We propose a novel attention mechanism, called Compositional Attention, that replaces the standard head structure.
  arXiv  Detail & Related papers  (2021-10-18T15:47:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.