Hello Participants,
We are excited to announce the winners of the Meta CRAG Challenge 2024. We appreciate your patience as we completed the due diligence process for the annotations.
We want to thank all participants for their efforts and contributions to improve RAG solutions. Over the last four months, the Meta CRAG Challenge has seen over 2000 participants from various countries, making over 5500 submissions. Below are the winners for each task. The final evaluation process can be found here: Final Evaluation Process & Team Scores
Task 1: Retrieval Summarization
Team db3
Team md_dh
Team ElectricSheep
Simple_w_condition Question: Team dummy_model
Set Question: Team dummy_model
Comparison Question: Team dRAGonRAnGers
Aggregation Question: Team dummy_model
Multi-hop Question: Team bumblebee7
Post-processing Question: Team dRAGonRAnGers
False Premise Question: Team ETSLab
Task 2: Knowledge Graph and Web Retrieval
Team db3
Team APEX
Team md_dh
Simple_w_condition Question: Team ElectricSheep
Set Question: Team ElectricSheep
Comparison Question: Team dRAGonRAnGers
Aggregation Question: Team ElectricSheep
Multi-hop Question: Team ElectricSheep
Post-processing Question: Team ElectricSheep
False Premise Question: Team Future
Task 3: End-to-End Retrieval-Augmented Generation
Team db3
Team APEX
Team vslyu-team
Simple_w_condition Question: Team StarTeam
Set Question: Team md_dh
Comparison Question: Team dRAGonRAnGers
Aggregation Question: Team md_dh
Multi-hop Question: Team ETSLab
Post-processing Question: Team md_dh
False Premise Question: Team Riviera4
We welcome all teams to submit a technical report to the 2024 KDD Cup RAG Workshop. The report should follow the KDD submission format.
- Submission link: OpenReview
- Submission deadline: 11:59 UTC, Aug 2, 2024
- Submission format: Submissions are limited to 8 pages (excluding references), must be in PDF, and use the ACM Conference Proceeding template (two-column format). For more details, please refer to: KDD 2024 ADS Track Call for Papers
We extend our sincere gratitude to all participants who contributed to this event!
All the best,
Meta & AIcrowd