arXiv AI

The Popular Get More Popular: Auditing Brand Bias in Generative Search

The paper audits brand bias in generative search, focusing on two dimensions: brand popularity bias and brand familiarity bias. It finds that dominant brands appear 1.4x to 2.8x more often than average brands in commercial queries, and that unfamiliar brand signatures significantly lower recommendation rank while fact-preserving rewrites have little effect. These results show that generative search engines reinforce a rich‑get‑richer dynamic, favoring established market leaders and creating a parametric barrier to entry that standard content optimization cannot overcome.

arXiv Computation and Language
Oct 22

Controlling Output Rankings in LLM-Based Search via Generative Engine Optimization

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
Hugging Face Trending Papers
Nov 8

Query- and Candidate-Aware Long User Sequence Modeling for Sponsored Product Ranking in Search

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.

arXiv Computation and Language
Sep 7

Repeated Queries Exhaust an LLM's Brand Recommendations but Not Its Sources

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 Machine Learning
Jul 28

SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads

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 AI
Sep 11

Query Brand Entity Linking in E-Commerce Search

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