4 papers
Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration
Zhimin Wang, Duo Wu, Shaokang He +6
Effective real-world multi-agent collaboration requires not only accurate planning but also the ability to reason about collaborators' intents--a crucial capability for avoiding mi…
Detecting Instruction Fine-tuning Attacks using Influence Function
Jiawei Li
Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintende…
Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts
Yunpeng Song, Jiawei Li, Yiheng Bian +1
Enhancing the intelligence of smart systems, such as smart home, and smart vehicle, and smart grids, critically depends on developing sophisticated planning capabilities that can a…
Delta-Influence: Unlearning Poisons via Influence Functions
Wenjie Li, Jiawei Li, Pengcheng Zeng +3
Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. St…