{"ID":2886477,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03628","arxiv_id":"2508.03628","title":"LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay","abstract":"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 systems and to maintain positive seller perception. It is vital that keyphrase suggestions align with seller, Search, and buyer judgments. Given the challenges in collecting negative feedback in these systems, LLMs have been used as a scalable proxy for human judgments. We present an empirical study on a major e-commerce platform of a distillation framework involving an LLM teacher, a cross-encoder assistant and a bi-encoder Embedding Based Retrieval (EBR) student model, aimed at mitigating click-induced biases and provide more diverse keyphrase recommendations while aligning advertising, search and buyer preferences.","short_abstract":"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 systems and to maintain positive seller perception. It is vital that keyphrase suggestions align with seller, Search, and buyer judgments. Given...","url_abs":"https://arxiv.org/abs/2508.03628","url_pdf":"https://arxiv.org/pdf/2508.03628v6","authors":"[\"Soumik Dey\",\"Benjamin Braun\",\"Naveen Ravipati\",\"Hansi Wu\",\"Binbin Li\"]","published":"2025-08-05T16:47:17Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}