| Automated Crossword Solving | 0 | 0.34 | 2022 |
| Analyzing Dynamic Adversarial Training Data in the Limit | 0 | 0.34 | 2022 |
| Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models | 0 | 0.34 | 2022 |
| Detoxifying Language Models Risks Marginalizing Minority Voices | 0 | 0.34 | 2021 |
| Calibrate Before Use: Improving Few-Shot Performance of Language Models | 0 | 0.34 | 2021 |
| Concealed Data Poisoning Attacks on NLP Models | 0 | 0.34 | 2021 |
| Extracting Training Data from Large Language Models | 0 | 0.34 | 2021 |
| Imitation Attacks and Defenses for Black-box Machine Translation Systems. | 0 | 0.34 | 2020 |
| AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts. | 0 | 0.34 | 2020 |
| Interpreting Predictions of NLP Models. | 0 | 0.34 | 2020 |
| Evaluating Models' Local Decision Boundaries via Contrast Sets. | 0 | 0.34 | 2020 |
| Gradient-based Analysis of NLP Models is Manipulable | 0 | 0.34 | 2020 |
| Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers | 0 | 0.34 | 2020 |
| Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples. | 0 | 0.34 | 2019 |
| Do NLP Models Know Numbers? Probing Numeracy in Embeddings | 2 | 0.38 | 2019 |
| AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models | 0 | 0.34 | 2019 |
| Universal Adversarial Triggers for Attacking and Analyzing NLP | 10 | 0.58 | 2019 |
| Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation. | 0 | 0.34 | 2019 |
| Pathologies of Neural Models Make Interpretation Difficult. | 4 | 0.38 | 2018 |
| Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions. | 2 | 0.36 | 2018 |
| Interpreting Neural Networks With Nearest Neighbors. | 0 | 0.34 | 2018 |
