ORQA

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

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

Natural Language Processing2 results

Question AnsweringonWebQuestions
EM· 2019-06-01
36.4
best: 84.6 (PoG-GPT4 (Tan et al., 2024))
SOTA
Latent Retrieval for Weakly Supervised Open Domain Question Answering arXiv:1906.00300
Question AnsweringonTriviaQA
EM· 2019-06-01
45
best: 87.5 (Claude 2 (few-shot, k=5))
Latent Retrieval for Weakly Supervised Open Domain Question Answering arXiv:1906.00300