ColBERTv2

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Information RetrievalonPeerQA
MRR· 2021-12-02
0.4122
best: 0.4845 (Dragon+)
SOTA
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction arXiv:2112.01488
Information RetrievalonPeerQA
Recall@10· 2021-12-02
0.6371
best: 0.6851 (SPLADEv3)
SOTA
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction arXiv:2112.01488