What Evidence Do Language Models Find Convincing? ACL

Alexander Wan | Eric Wallace | Dan Klein |

Automated Crossword Solving ACL

Eric Wallace | Nicholas Tomlin | Albert Xu | Kevin Yang | Eshaan Pathak | Matthew Ginsberg | Dan Klein |

Analyzing Dynamic Adversarial Training Data in the Limit ACL Findings

Eric Wallace | Adina Williams | Robin Jia | Douwe Kiela |

Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models ACL Findings

Robert Logan IV | Ivana Balazevic | Eric Wallace | Fabio Petroni | Sameer Singh | Sebastian Riedel |

Concealed Data Poisoning Attacks on NLP Models NAACL

Eric Wallace | Tony Zhao | Shi Feng | Sameer Singh |

Detoxifying Language Models Risks Marginalizing Minority Voices NAACL

Albert Xu | Eshaan Pathak | Eric Wallace | Suchin Gururangan | Maarten Sap | Dan Klein |

Pretrained Transformers Improve Out-of-Distribution Robustness ACL

Dan Hendrycks | Xiaoyuan Liu | Eric Wallace | Adam Dziedzic | Rishabh Krishnan | Dawn Song |

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts EMNLP

Taylor Shin | Yasaman Razeghi | Robert L. Logan IV | Eric Wallace | Sameer Singh |

Imitation Attacks and Defenses for Black-box Machine Translation Systems EMNLP

Eric Wallace | Mitchell Stern | Dawn Song |

Interpreting Predictions of NLP Models EMNLP

Eric Wallace | Matt Gardner | Sameer Singh |

Gradient-based Analysis of NLP Models is Manipulable EMNLP Findings

Junlin Wang | Jens Tuyls | Eric Wallace | Sameer Singh |

Evaluating Models’ Local Decision Boundaries via Contrast Sets EMNLP Findings

Matt Gardner | Yoav Artzi | Victoria Basmov | Jonathan Berant | Ben Bogin | Sihao Chen | Pradeep Dasigi | Dheeru Dua | Yanai Elazar | Ananth Gottumukkala | Nitish Gupta | Hannaneh Hajishirzi | Gabriel Ilharco | Daniel Khashabi | Kevin Lin | Jiangming Liu | Nelson F. Liu | Phoebe Mulcaire | Qiang Ning | Sameer Singh | Noah A. Smith | Sanjay Subramanian | Reut Tsarfaty | Eric Wallace | Ally Zhang | Ben Zhou |

Universal Adversarial Triggers for Attacking and Analyzing NLP EMNLP

Eric Wallace | Shi Feng | Nikhil Kandpal | Matt Gardner | Sameer Singh |

Do NLP Models Know Numbers? Probing Numeracy in Embeddings EMNLP

Eric Wallace | Yizhong Wang | Sujian Li | Sameer Singh | Matt Gardner |

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models EMNLP

Eric Wallace | Jens Tuyls | Junlin Wang | Sanjay Subramanian | Matt Gardner | Sameer Singh |

Compositional Questions Do Not Necessitate Multi-hop Reasoning ACL

Sewon Min | Eric Wallace | Sameer Singh | Matt Gardner | Hannaneh Hajishirzi | Luke Zettlemoyer |

Misleading Failures of Partial-input Baselines ACL

Shi Feng | Eric Wallace | Jordan Boyd-Graber |

Trick Me If You Can: Human-in-the-Loop Generation of Adversarial Examples for Question Answering TACL

Eric Wallace | Pedro Rodriguez | Shi Feng | Ikuya Yamada | Jordan Boyd-Graber |

Pathologies of Neural Models Make Interpretations Difficult EMNLP

Shi Feng | Eric Wallace | Alvin Grissom II | Mohit Iyyer | Pedro Rodriguez | Jordan Boyd-Graber |

Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions ACL

Eric Wallace | Jordan Boyd-Graber |

Interpreting Neural Networks with Nearest Neighbors EMNLP WS

Eric Wallace | Shi Feng | Jordan Boyd-Graber |