Eric Wallace
Sandia National Laboratories(US)OpenAI (United States)(US)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Adversarial Robustness in Machine Learning, Explainable Artificial Intelligence (XAI), Multimodal Machine Learning Applications
Most-Cited Works
- → AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts(2020)1,134 cited
- → Pretrained Transformers Improve Out-of-Distribution Robustness(2020)290 cited
- → Extracting Training Data from Large Language Models(2020)274 cited
- → Evaluating Models’ Local Decision Boundaries via Contrast Sets(2020)255 cited
- → Pathologies of Neural Models Make Interpretations Difficult(2018)237 cited
- → Compositional Questions Do Not Necessitate Multi-hop Reasoning(2019)129 cited
- → Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models(2022)126 cited
- → AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models(2019)125 cited
- Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers(2020)
- → Calibrate Before Use: Improving Few-Shot Performance of Language Models(2021)72 cited