Xianglong Liu

4 papers Beihang University, Tsinghua University

• Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text
• Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
• Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
• Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction