Paper | Code | KILT-RL | R-Prec | Recall@5 | ROUGE-L | F1 | KILT-F1 | ModelName | ReleaseDate |
---|---|---|---|---|---|---|---|---|---|
[]() | 2.62 | 10.83 | 27.25 | 24.53 | 27.13 | 3.0 | somebody | ||
[]() | 2.46 | 14.83 | 27.69 | 16.45 | 15.91 | 2.38 | Wikipedia | ||
Hurdles to Progress in Long-form Question Answering | ✓ Link | 2.36 | 10.67 | 24.56 | 23.19 | 22.88 | 2.34 | arxiv.org/abs/2103.06332 | 2021-03-10 |
[]() | 1.9 | 10.67 | 26.92 | 17.41 | 17.88 | 2.01 | BART + DPR | ||
[]() | 1.69 | 11.0 | 22.92 | 14.05 | 14.51 | 1.79 | RAG | ||
[]() | 0.0 | 18.33 | 28.21 | 0.0 | 0.0 | 0.0 | TABi | ||
[]() | 0.0 | 17.5 | 25.54 | 0.0 | 0.0 | 0.0 | chriskuei | ||
[]() | 0.0 | 15.83 | 25.49 | 0.0 | 0.0 | 0.0 | GENRE | ||
[]() | 0.0 | 15.5 | 27.51 | 0.0 | 0.0 | 0.0 | Multi-task DPR | ||
[]() | 0.0 | 0.0 | 0.0 | 20.55 | 19.23 | 0.0 | BART | ||
KILT: a Benchmark for Knowledge Intensive Language Tasks | ✓ Link | 0.0 | 0.0 | 0.0 | 19.08 | 16.1 | 0.0 | T5-base | 2020-09-04 |
[]() | 0.0 | 0.0 | 0.0 | 18.66 | 21.62 | 0.0 | Training Set Retrieval (top 1) | ||
[]() | 0.0 | 0.0 | 0.0 | 17.67 | 16.4 | 0.0 | multi-task small | ||
[]() | 0.0 | 0.0 | 0.0 | 16.88 | 14.8 | 0.0 | Input Copying | ||
[]() | 0.0 | 0.0 | 0.0 | 15.76 | 15.29 | 0.0 | Sphere | ||
[]() | 0.0 | 0.0 | 0.0 | 15.45 | 17.07 | 0.0 | Random Training Set Answer |