To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBay
This work addresses the challenge of maintaining search system health and seller perception in e-commerce advertising, though it appears incremental by applying existing LLM methods to a specific domain.
The study tackled the problem of aligning advertiser keyphrase relevance models with human judgment to improve e-commerce search systems, demonstrating that using LLM judgments as a scalable proxy achieves better harmony across seller, advertising, and search systems when bound by a meticulous evaluation framework.
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 plays an important role in preventing the inundation of search systems with numerous irrelevant items that compete for attention in auctions, in addition to maintaining a healthy seller perception. In this work, we describe the shortcomings of training Advertiser keyphrase relevance filter models on click/sales/search relevance signals and the importance of aligning with human judgment, as sellers have the power to adopt or reject said keyphrase recommendations. In this study, we frame Advertiser keyphrase relevance as a complex interaction between 3 dynamical systems -- seller judgment, which influences seller adoption of our product, Advertising, which provides the keyphrases to bid on, and Search, who holds the auctions for the same keyphrases. This study discusses the practicalities of using human judgment via a case study at eBay Advertising and demonstrate that using LLM-as-a-judge en-masse as a scalable proxy for seller judgment to train our relevance models achieves a better harmony across the three systems -- provided that they are bound by a meticulous evaluation framework grounded in business metrics.