Maximilian Mozes

Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e.g., the …

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

2024 · arXiv (Cornell University)

The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand, LLMs demonstrate a general ability to solve …