COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon
Summary: COSMO: scalable pipeline to mine user-centric commonsense from behaviors, with LLM seeds refined by critic classifiers. COSMO-LM is instruction-tuned to expand KG to 18, delivering millions of facts from 30k annotations, deployed in Amazon search. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Changlong Yu
- 2. Xin Liu
- 3. Jefferson Maia
- 4. Yang Li
- 5. Tianyu Cao
- 6. Yifan Gao
- 7. Yangqiu Song
- 8. Rahul Goutam
- 9. Haiyang Zhang
- 10. Bing Yin
- 11. Zheng Li
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,560 | RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search | 2024 | VLDB | 6.6961568e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,915 | Elastic Machine Learning Algorithms in Amazon SageMaker | 2020 | SIGMOD | 9.5806135e-05 |
| 4,283 | AliCoCo: Alibaba E-commerce Cognitive Concept Net | 2020 | SIGMOD | 6.8542494e-05 |
Previous
Page 1 / 1
Next