Yonatan Belinkov, Desmond Elliott, Mostafa Abdou, Anders Søgaard, Vinit Ravishankar, Maria Barrett
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of commonsense reasoning ability. We show, however, with a new diagnostic dataset, that these models are sensitive to linguistic perturbations of the Winograd examples that minimally affect human understanding. Our results highlight interesting differences between humans and language models: language models are more sensitive to number or gender alternations and synonym replacements than humans, and humans are more stable and consistent in their predictions, maintain a much higher absolute performance, and perform better on non-associative instances than associative ones. Overall, humans are correct more often than out-of-the-box models, and the models are sometimes right for the wrong reasons. Finally, we show that fine-tuning on a large, task-specific dataset can offer a solution to these issues.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2005.01348")
get_code_for_paper("2005.01348")
have("2005.01348")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2005.01348.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2005.01348)
Connect an agent — have() is free.