Common Sense Reasoning
Common sense reasoning tasks are intended to require the model to go beyond pattern recognition. Instead, the model should use "common sense" or world knowledge to make inferences.
Papers
Showing 1–10 of 939 papers
All datasetsWinoGrandearc_challengearc_easyReCoRDCommonsenseQAPARusRuCoSRWSDBIG-bench (Causal Judgment)BIG-bench (Date Understanding)BIG-bench (Disambiguation QA)BIG-bench (Sports Understanding)
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Human Benchmark | Average F1 | 0.93 | — | Unverified |
| 2 | Golden Transformer | Average F1 | 0.92 | — | Unverified |
| 3 | YaLM 1.0B few-shot | Average F1 | 0.86 | — | Unverified |
| 4 | ruT5-large-finetune | Average F1 | 0.81 | — | Unverified |
| 5 | ruT5-base-finetune | Average F1 | 0.79 | — | Unverified |
| 6 | ruBert-base finetune | Average F1 | 0.74 | — | Unverified |
| 7 | ruRoberta-large finetune | Average F1 | 0.73 | — | Unverified |
| 8 | ruBert-large finetune | Average F1 | 0.68 | — | Unverified |
| 9 | RuGPT3XL few-shot | Average F1 | 0.67 | — | Unverified |
| 10 | MT5 Large | Average F1 | 0.57 | — | Unverified |