activity
20242026
collaborators
Showing cs.IRShow all

7 papers · 1 filter

cs.IR2026

LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay

Soumik Dey, Benjamin Braun, Naveen Ravipati +2

E-commerce sellers are advised to bid on keyphrases to boost their advertising campaigns. These keyphrases must be relevant to prevent irrelevant items from cluttering Search syste…

cs.IR2025

BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendations

Ashirbad Mishra, Jinyu Zhao, Soumik Dey +3

In the domain of sponsored search advertising, the focus of Keyphrase recommendation has largely been on exact match types, which pose issues such as high management expenses, limi…

cs.IR2025

To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBay

Soumik Dey, Hansi Wu, Binbin Li

E-commerce sellers are recommended keyphrases based on their inventory on which they advertise to increase buyer engagement (clicks/sales). The relevance of advertiser keyphrases p…

cs.IR2025

GraphEx: A Graph-based Extraction Method for Advertiser Keyphrase Recommendation

Ashirbad Mishra, Soumik Dey, Marshall Wu +5

Online sellers and advertisers are recommended keyphrases for their listed products, which they bid on to enhance their sales. One popular paradigm that generates such recommendati…

cs.IR2025

Middleman Bias in Advertising: Aligning Relevance of Keyphrase Recommendations with Search

Soumik Dey, Wei Zhang, Hansi Wu +2

E-commerce sellers are recommended keyphrases based on their inventory on which they advertise to increase buyer engagement (clicks/sales). Keyphrases must be pertinent to items; o…

cs.IR2025

From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning

Ranran Haoran Zhang, Bensu Uçar, Soumik Dey +3

Open-vocabulary Extreme Multi-label Classification (OXMC) extends traditional XMC by allowing prediction beyond an extremely large, predefined label set (typically to $10^{1…