Eric Wallace

Universal Adversarial Triggers for Attacking and Analyzing NLP

2019

Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Deduplicating Training Data Mitigates Privacy Risks in Language Models

2022 · arXiv (Cornell University)

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we …

Automated Crossword Solving

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Eric Wallace, Nicholas Tomlin, Albert Xu, Kevin Yang, Eshaan Pathak, Matthew Ginsberg, Dan Klein. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

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

2021 · arXiv (Cornell University)

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably …

Compositional Questions Do Not Necessitate Multi-hop Reasoning

2019

Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC datasets. For example, even highly compositional questions …

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

2020

The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fillin-the-blanks problems (e.g., cloze tests) is a natural approach for gauging …

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

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably …