Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Intelligent agents must be generalists, capable of quickly adapting to various tasks.

If a relaxation's solution satisfies the integer requirements, it is a valid solution to

By exploiting students' response logs, SCM aims to predict their exercise

To avoid redundancy in these synthetic datasets, it is crucial that each element contains unique features and remains diverse from others during the synthesis stage. In this paper, we provide a thorough theoretical and empirical analysis of diversity within synthesized datasets. We argue that enhancing diversity can improve the parallelizable yet isolated synthesizing approach.

To further verify this finding, we empirically show that these dormant backdoors can be easily re-activated during inference stage, by manipulating the original trigger with well-designed tiny perturbation using universal adversarial attack.

Large Language Models (LLMs) are widely used in today's tasks of natural language processing.