Ze Yang

Learning to Copy Coherent Knowledge for Response Generation

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Knowledge-driven dialog has shown remarkable performance to alleviate the problem of generating uninformative responses in the dialog system. However, incorporating knowledge coherently and accurately into response generation is still far from being solved. Previous works …

TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization

2022 · arXiv (Cornell University)

Although pre-trained language models (PLMs) have achieved great success and become a milestone in NLP, abstractive conversational summarization remains a challenging but less studied task. The difficulty lies in two aspects. One is the lack …

Adversarial Prompt Optimization in LLMs: HijackNet’s Approach to Robustness and Defense Evasion

2025 · Preprints.org

This paper introduces HijackNet, an adversarial prompt hijacking framework designed to improve hijacking success rates and generalization in multi-lingual tasks. Combining Neural Architecture Search (NAS), Reinforcement Learning (RL), and Multi-Objective Optimization (MOO), HijackNet generates adversarial …