Paper | Code | KILT-RL | R-Prec | Recall@5 | ROUGE-L | F1 | KILT-F1 | ModelName | ReleaseDate |
---|---|---|---|---|---|---|---|---|---|
[]() | 11.92 | 56.08 | 74.27 | 17.06 | 19.19 | 13.39 | Hindsight | ||
Re2G: Retrieve, Rerank, Generate | ✓ Link | 11.39 | 60.1 | 79.98 | 16.76 | 18.9 | 12.98 | Re2G | 2022-07-13 |
[]() | 10.45 | 57.55 | 78.96 | 16.65 | 18.34 | 11.63 | intersect | ||
[]() | 10.36 | 55.37 | 78.45 | 16.36 | 18.57 | 11.79 | KGI | ||
[]() | 7.59 | 57.75 | 74.61 | 11.57 | 13.11 | 8.75 | RAG | ||
[]() | 6.55 | 41.54 | 68.25 | 13.94 | 15.66 | 7.57 | Wikipedia | ||
[]() | 5.91 | 41.06 | 67.13 | 13.27 | 15.12 | 6.96 | Multitask DPR + BART | ||
[]() | 4.41 | 39.06 | 51.63 | 11.42 | 12.15 | 4.8 | Routing Transformer, c-REALM | ||
[]() | 3.71 | 25.46 | 51.19 | 13.23 | 15.19 | 4.37 | BART + DPR | ||
[]() | 2.04 | 55.71 | 75.59 | 2.92 | 3.09 | 2.18 | multitask | ||
[]() | 1.85 | 18.35 | 18.35 | 10.11 | 11.85 | 2.2 | TransMemNet | ||
[]() | 0.0 | 64.79 | 82.15 | 0.0 | 0.0 | 0.0 | chriskuei | ||
[]() | 0.0 | 62.88 | 77.74 | 0.0 | 0.0 | 0.0 | GENRE | ||
[]() | 0.0 | 59.11 | 69.1 | 0.0 | 0.0 | 0.0 | TABi | ||
[]() | 0.0 | 41.06 | 67.13 | 0.0 | 0.0 | 0.0 | Multi-task DPR | ||
[]() | 0.0 | 0.0 | 0.0 | 15.93 | 17.3 | 0.0 | aa_evalai | ||
[]() | 0.0 | 0.0 | 0.0 | 15.71 | 17.28 | 0.0 | Sphere | ||
[]() | 0.0 | 0.0 | 0.0 | 13.35 | 14.82 | 0.0 | bart-base | ||
[]() | 0.0 | 0.0 | 0.0 | 12.81 | 13.75 | 0.0 | multi-task small | ||
KILT: a Benchmark for Knowledge Intensive Language Tasks | ✓ Link | 0.0 | 0.0 | 0.0 | 12.4 | 13.53 | 0.0 | T5-base | 2020-09-04 |
[]() | 0.0 | 0.0 | 0.0 | 11.77 | 12.86 | 0.0 | BART |