Jonathan Herzig

Learning To Retrieve Prompts for In-Context Learning

2021 · arXiv (Cornell University)

In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without …

TRUE: Re-evaluating Factual Consistency Evaluation

2022 · arXiv (Cornell University)

Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability. Automatic factual consistency evaluation may help alleviate this limitation by accelerating evaluation cycles, filtering inconsistent outputs and augmenting training data. …

CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

2018 · arXiv (Cornell University)

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very …

Learning To Retrieve Prompts for In-Context Learning

2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

In-context learning is a recent paradigm in natural language understanding, where a large pretrained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without …