e commerce

1
RPTune: Learned Context Curation for LLM Catalog Search arxiv.org
RPTune is an end‑to‑end system that learns to curate product catalogs for in‑context LLM search and fine‑tunes the LLM with a context‑relative reward. On seven real merchants it boosts search accuracy by up to 31 pp from curation and an additional ~10 pp from post‑training.
Hugging Face Daily Papersarxiv.orgChuxuan Hu, Hejie Cui, Norman Huang5d1 minpaper
2
ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker arxiv.org
ZooWork-ShopRanker is a family of open e-commerce rerankers (0.6B, 4B, 8B) trained using preference labels generated by an ensemble of LLMs. The 8B model, aligned to judge-labeled shopping preferences, significantly outperforms strong open reranker baselines on a new benchmark, ShopRank-Bench.
Hugging Face Daily Papersarxiv.orgSiqiao Xue, Shuxuan Liu, Ning Hu11d1 minpaper

RPTune: Learned Context Curation for LLM Catalog Searcharxiv.org