ColBERT

Reported on 5 benchmarks across 4 tasks · 1 paper

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

Natural Language Processing2 results

Question AnsweringonNQ (BEIR)
nDCG@10· 2021-04-17
0.524
best: 0.67 (Blended RAG)
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models arXiv:2104.08663
Information RetrievalonMSMARCO (BEIR)
nDCG@10· 2021-04-17
0.401
best: 0.413 (BM25+CE)
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models arXiv:2104.08663

Medical2 results

Biomedical Information RetrievalonNFCorpus (BEIR)
nDCG@10· 2021-04-17
0.305
best: 0.383 (monoT5-3B)
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models arXiv:2104.08663
Biomedical Information RetrievalonTREC-COVID (BEIR)
nDCG@10· 2021-04-17
0.677
best: 0.873 (SGPT-BE-5.8B)
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models arXiv:2104.08663

Miscellaneous1 result

Fact CheckingonSciFact (BEIR)
nDCG@10· 2021-04-17
0.671
best: 0.777 (monoT5-3B)
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models arXiv:2104.08663