Can training neural language models on a curriculum with developmentally plausible data improve alignment with human reading behavior? CoNLL

Aryaman Chobey | Oliver Smith | Anzi Wang | Grusha Prasad |

Dynabench: Rethinking Benchmarking in NLP NAACL

Douwe Kiela | Max Bartolo | Yixin Nie | Divyansh Kaushik | Atticus Geiger | Zhengxuan Wu | Bertie Vidgen | Grusha Prasad | Amanpreet Singh | Pratik Ringshia | Zhiyi Ma | Tristan Thrush | Sebastian Riedel | Zeerak Waseem | Pontus Stenetorp | Robin Jia | Mohit Bansal | Christopher Potts | Adina Williams |

To what extent do human explanations of model behavior align with actual model behavior? BlackboxNLP EMNLP

Grusha Prasad | Yixin Nie | Mohit Bansal | Robin Jia | Douwe Kiela | Adina Williams |

Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction CoNLL EMNLP

Shauli Ravfogel | Grusha Prasad | Tal Linzen | Yoav Goldberg |

Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models CoNLL

Grusha Prasad | Marten van Schijndel | Tal Linzen |