Mistral multi hop with very large sources
Reported on 6 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing6 results
- ANS-EM0.08best: 0.727 (Beam Retrieval)
- ANS-F10.221best: 0.85 (Beam Retrieval)
- JOINT-EM0best: 0.505 (Beam Retrieval)
- JOINT-F10best: 0.775 (Beam Retrieval)
- SUP-EM0best: 0.663 (Beam Retrieval)
- SUP-F10best: 0.901 (Beam Retrieval)