ZooWork-ShopRanker: open e-commerce rerankers (0.6B-8B) aligned to shopping preferences
kalyan_kpl · x · 2026-10-08
- Open rerankers trained for general web retrieval transfer poorly to e-commerce, where ranking also depends on user preferences, product constraints and comparative fit.
- ZooWork-ShopRanker is a family of open e-commerce rerankers (0.6B, 4B, 8B) aligned to judge-labeled shopping preferences, with training pairs labeled by a panel of reasoning LLMs from different families.
- The aligned 8B flagship serves as a distillation teacher for the efficient 4B and 0.6B models, sharpened on judged pairs.
- The team also released ShopRank-Bench, a contamination-limited benchmark of 10,000 private-traffic preference pairs.
More from Research
- ProactiveCoach: Hierarchical Guidance Boosts Proactive AI Assistants by 57.1 Points — skku · 2026-10-08
- STEPQuant: 6-bit quantization of Delta-rule recurrent states cuts serving memory by up to 68.7% — zju-community · 2026-10-08
- RoboQuest Benchmark: Best Multimodal Agent Succeeds in Only 23% of Embodied Exploration Tasks — declare-lab · 2026-10-08
- KAIST's GRACE cuts Wan2.1-I2V video generation latency by 11.1x with generation-aware latent compression — kaist-ai · 2026-10-08
- NVIDIA's Long-WAM scales world-action model context, hitting 95% on dynamic cup stacking — nvidia · 2026-10-08
- RobotWorld Benchmark Tests Multimodal Agents on 84 Physical Robot Tasks — Zhiqin Yang · 2026-10-08