Papers with Code · CC BY-SA 4.0

Common Sense Reasoning

430 평가 기록 38 datasets

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.

하위 태스크

PC Physical Commonsense Reasoning 1 데이터셋 · 6 rows RS Riddle Sense 2 데이터셋 · 5 rows CA Crass AI 1 데이터셋 · 4 rows MC Multiview Contextual Commonsense Inference 2 데이터셋 · 4 rows CB Crash Blossom 1 데이터셋 · 2 rows DM Discourse Marker Prediction 1 데이터셋 · 2 rows EJ Empirical Judgments 1 데이터셋 · 2 rows II Irony Identification 1 데이터셋 · 2 rows T Timedial 1 데이터셋 · 2 rows UF Understanding Fables 1 데이터셋 · 2 rows VC Visual Commonsense Tests 1 데이터셋 · 2 rows A Anachronisms 0 데이터셋 · 0 rows CJ Causal Judgment 0 데이터셋 · 0 rows DQ Disambiguation QA 0 데이터셋 · 0 rows H HellaSwag 0 데이터셋 · 0 rows W Winogrande 1 데이터셋 · 0 rows W Winowhy 0 데이터셋 · 0 rows