1 |
To what extent do human explanations of model behavior align with actual model behavior? ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|