← Back to papers

2023 IJCNLP IJCNLP 2023

Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge

Authors

Manuel Brack , Patrick Schramowski , Kristian Kersting

Related papers

On the Use of Language Models for Function Identification of Citations in Scholarly Papers 2023

Team NLLG submission for Eval4NLP 2023 Shared Task: Retrieval-Augmented In-Context Learning for NLG Evaluation 2023

Automatic Translation of Span-Prediction Datasets 2023

PACT: Pretraining with Adversarial Contrastive Learning for Text Classification 2023

VACASPATI: A Diverse Corpus of Bangla Literature 2023