The paper introduces Mine and Refine, a two‑stage contrastive training framework designed to improve embedding‑based retrieval for large‑scale e‑commerce search. It tackles graded relevance, hard‑sample mining, and unstable similarity separability by using a lightweight LLM as a scalable labeler and a multi‑level circle loss to enforce margin‑controlled separation across relevance levels. The method has been deployed in production across multiple product verticals, yielding statistically significant increases in user engagement, gross order value, and retrieval relevance metrics.
By Jiaqi Xi, Raghav Saboo, Luming Chen, Johny Rufus, Aditya Dodda, Ved Sampath, Kenny Chi, Elyse Winer, Akshad Viswanathan, Martin Wang, Sudeep Das
RPTune is an end‑to‑end framework that improves in‑context catalog search for small merchant businesses by learning to curate product catalogs and fine‑tuning large language models (LLMs) with catalog‑grounded supervision. It uses an encoder‑reorganizer curator to order and prune products based on LLM feedback, and then applies context‑relative rewards during LLM post‑training. Across seven real merchants and 100 complex conversational queries per merchant, RPTune boosts search accuracy by up to 31.4 percentage points from curation alone and an additional 10.3 points on average from post‑training.
By Chuxuan Hu, Hejie Cui, Norman Huang, Shubham Kumar Bharti, Wang-Chiew Tan, Sercan \"O. Ar{\i}k
arXiv:2609.23646v1 Announce Type: cross
Abstract: E-commerce search requires distinguishing products that are merely related to a query from those that directly satisfy the user's shopping intent. We...
By Girish A. Koushik, Swapnil Bhosale, Samarth Agrawal, Hadeel Sadany, Constantin Orasan, Xiatian Zhu, Diptesh Kanojia
arXiv:2607. 23121v1 Announce Type: cross Abstract: Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and prospecting (discovering new categories).
By Congfei Zhang, Jingxiao Ma, Xiaodong Liu, Hsiang-wei Chao, Siman Wang, Ge Liu, Shantanu Aggarwal, Vincent Zhang, Meghana Missula, Rachel Liao, Zichu Li, Xiao Bai, Yunzhi Zhou, Yajun Wang, Zhe Liu, Jinchao Li, Yu Zhang
arXiv:2608.30753v1 Announce Type: cross
Abstract: In large-scale e-commerce retrieval, dual-encoder retrievers are op- timized for contrastive similarity, whereas downstream rerankers capture finer-g...
By Shaowei Wei, Chong Huang, Songtao Fang, Jin Zhang, Zhuojun Wang, Chengfu Huo
The paper proposes a single hierarchical Semantic ID (SID) system to unify product identification across multiple merchants in e-commerce. By learning SID representations from product content, the authors demonstrate that ranking algorithms can aggregate consumer affinity and product performance over SID prefixes, improving offline relevance and online engagement. For query reformulation, SID concepts guide navigation and refinement, yielding better intent preservation and higher-quality suggestions compared to taxonomy or raw query transitions.
By Steven Xu, Sanjyot Thete, Saathvik Dirisala, Raghav Saboo, Nimesh Sinha, Leo Shao, Elyse Winer, Sudeep Das, Martin Wang, Kyle MacDonald
ZooWork-ShopRanker is a family of open e‑commerce rerankers (0.6B, 4B, and 8B) that align with human shopping preferences by using large language models as preference oracles to generate training pairs. The flagship 8B model serves as a teacher for the smaller 4B and 0.6B models, which are further refined on judged pairs. A new benchmark, ShopRank‑Bench, contains ~10,000 private‑traffic preference pairs and shows that all ZooWork models outperform the strongest open reranker baseline and their own un‑aligned versions.
By Siqiao Xue, Shuxuan Liu, Ning Hu
arXiv:2607. 27172v1 Announce Type: cross Abstract: Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall.
By Ji Xin, Xiao Xiao, Ishan Bhatt, Vinesh Gudla, Trace Levinson, Raochuan Fan, Shishir Kumar Prasad, Prakash Putta, Tejaswi Tenneti
The paper introduces GradCIR, a method for training composed image retrieval (CIR) systems on graded relevance rather than binary relevance. It uses a vision‑language model to generate queries and 4‑level relevance labels, an iterative feedback loop to mine hard negatives, and a hierarchy‑aware angular objective to directly optimize graded labels. Experiments on a Walmart catalog and FashionIQ show significant NDCG improvements and the system is deployed in Walmart’s live visual‑search traffic.
By Anubhav Gupta, Hrushikesh Mohapatra, Prijith Chandra, Asish Mohapatra, Anuj Garg, Arvind Maan, Sudip Datta, Venkat Bulusu, Sitesh Kumar Jalan
Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall. In e-commerce marketplaces and particularly grocery, this paradigm is limiting, as user satisfaction and commercial outcomes depend heavily on the discoverability of substitute, complementary, and thematically related items.
arXiv:2606. 04374v1 Announce Type: cross Abstract: Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions.
By Bokang Wang, Xing Fang, Mingmin Jin, Jing Wang, Zhentao Song, Guangxin Song, Jianbo Zhu
The paper "Query Brand Entity Linking in E-Commerce Search" addresses the challenge of matching short, unstructured user search queries to the correct brand entities in large e‑commerce catalogs. It proposes two scalable solutions: a cascaded pipeline that first detects brand mentions and then disambiguates them, and a single‑stage extreme multiclass classifier that directly maps queries to brand identifiers. Extensive multilingual evaluation and an online experiment show that both methods significantly improve brand recall while preserving high precision, resulting in measurable gains in customer engagement.
By Dong Liu, Sreyashi Nag