ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker
cs.CL
Submitted: 2026-09-25
Updated: 2026-09-25
Comments: project page: \url{https://serendipityoneinc.github.io/look-bench-page/shoprank-bench.html}
License: http://creativecommons.org/licenses/by/4.0/
The gist: Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, product constraints,
Terminology
Abstract
Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, product constraints, and comparative product fit. These preference signals are difficult to supervise at scale: real search traffic provides authentic queries and candidates but no clean pairwise labels. We present ZooWork-ShopRanker, a family of e-commerce rerankers (0.6B, 4B, and 8B) aligned to judge-labeled shopping preference. Training pairs are labeled by a panel of reasoning large language models (LLMs) from different families acting as a preference oracle, with position-debiased judgments and agreement tiers, and the rerankers are trained on these labels. The aligned 8B flagship then serves as a distillation teacher for the efficient 4B and 0.6B models, which are fit to its scores and sharpened on judged pairs. To measure progress, we introduce ShopRank-Bench, a contamination-limited benchmark of 10,000 private-traffic preference pairs in both text formats, tiered by how many judge families committed to each label. ZooWork-ShopRanker-8B and-4B significantly outperform the strongest open reranker baseline, every model significantly beats its own un-aligned base, and ZooWork-ShopRanker-0.6B beats its size peer; the gains hold in both formats and extend to common MTEB benchmarks. We release the models and the dual-format ShopRank-Bench to facilitate further research.
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval
- jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
- LoRA: Low-Rank Adaptation of Large Language Models
- MTEB: Massive Text Embedding Benchmark
- jina-embeddings-v3: Multilingual Embeddings With Task LoRA
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval
- FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering
- Beyond Retrieval: A Multitask Benchmark and Model for Code Search
- QuitoBench: A High-Quality Open Time Series Forecasting Benchmark
- Qwen3 Technical Report
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering