arXiv:2610.19065v1 Announce Type: cross
Abstract: Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers...
By Renbo Tu, Yang Liu, Shuying Sun
The paper introduces CORE, an optimization method that controls output rankings in large language model (LLM)-based search engines by appending strategically designed optimization content—string-based, reasoning-based, and review-based—to the retrieved content. CORE targets the black-box nature of LLM interactions with search engines, steering the ranking of product recommendations. Experiments on four LLMs (GPT‑4o, Gemini‑2.5, Claude‑4, and Grok‑3) using the new ProductBench benchmark show that CORE achieves high promotion success rates (91.4% @Top‑5, 86.6% @Top‑3, 80.3% @Top‑1) across 15 product categories, outperforming existing ranking manipulation methods while maintaining content fluency.
By Haibo Jin, Huimin Zeng, Yifeng Luo, Haohan Wang
Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved. However, GR is not a uniformly stron...
arXiv:2606. 17443v1 Announce Type: new Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new channel.
By Xi Chu, Yupeng Hou
arXiv:2608.30023v1 Announce Type: cross
Abstract: Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying...
By Dmitrij \.Zatuchin, Daniil Dzemesjuk
arXiv:2606. 13610v1 Announce Type: cross Abstract: Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content.
By Minghao Luo, Liang Chen
arXiv:2603. 08924v2 Announce Type: replace-cross Abstract: AI-powered answer engines are inherently non-deterministic: identical queries submitted at different times can produce different responses and cite different sources.
By Ronald Sielinski
arXiv:2602. 23234v4 Announce Type: replace-cross Abstract: Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for.
By Evangelia Christakopoulou, Vivekkumar Patel, Hemanth Velaga, Sandip Gaikwad, Sean Suchter, Venkat Sundaranatha
The paper introduces a production sequence framework for sponsored‑product ranking that enriches recent user behavior with two retrieval channels over long‑term history: candidate‑nearest‑neighbor and query‑nearest‑neighbor retrieval. Selected actions are encoded with dedicated query and candidate context tokens, and candidate‑aware early fusion incorporates the candidate into every history token. Offline ablations and an online A/B test demonstrate that dual retrieval improves key ranking metrics, increasing CTR, attributed conversion rate, and orders per impression.
The study examines how repeated identical buying questions affect the brand recommendations of large language models (LLMs) with and without web‑search retrieval. Across 300 question‑engine cells, five engines that did not use web search continued to add new, previously unseen brands up to run 15, while the single retrieval‑enabled engine’s list plateaued earlier. Domain citations continued to grow throughout the runs, indicating that LLMs keep accumulating source diversity even as brand lists stabilize.
By Dmitrij \.Zatuchin
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
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