SocialIQA is the first large-scale benchmark with 38k crowdsourced questions testing commonsense about social interactions, where pretrained language models trail humans by over 20% but transfer to improve performance on Winograd Schemas and COPA.
NIPS-W , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Recurrent Transformers add per-layer recurrent memory via self-attention on own activations plus a tiling algorithm that reduces training memory traffic, yielding better C4 pretraining cross-entropy than parameter-matched standard transformers with fewer layers.
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
PIQA is a new benchmark showing that current AI models achieve 77% on physical commonsense questions versus humans at 95%.
citing papers explorer
-
SocialIQA: Commonsense Reasoning about Social Interactions
SocialIQA is the first large-scale benchmark with 38k crowdsourced questions testing commonsense about social interactions, where pretrained language models trail humans by over 20% but transfer to improve performance on Winograd Schemas and COPA.
-
PIQA: Reasoning about Physical Commonsense in Natural Language
PIQA is a new benchmark showing that current AI models achieve 77% on physical commonsense questions versus humans at 95%.