Conflict Classification
Conflict classification encompasses the identification and categorization of various types of conflicts, from geopolitical events and disinformation campaigns to internal inconsistencies within artificial intelligence models and conflicts between software code segments. Current research focuses on developing and refining methods for conflict detection and resolution using techniques like deep learning (particularly convolutional neural networks and transformers), multi-objective evolutionary algorithms, and information graph neural networks, often incorporating interpretability analysis to enhance trustworthiness. This field is crucial for improving humanitarian response, combating misinformation, enhancing AI robustness, and optimizing various technological and social systems, with applications ranging from damage assessment in conflict zones to improving software development processes and human-computer interaction.
Papers
SERN: Simulation-Enhanced Realistic Navigation for Multi-Agent Robotic Systems in Contested Environments
Jumman Hossain, Emon Dey, Snehalraj Chugh, Masud Ahmed, MS Anwar, Abu-Zaher Faridee, Jason Hoppes, Theron Trout, Anjon Basak, Rafidh Chowdhury, Rishabh Mistry, Hyun Kim, Jade Freeman, Niranjan Suri, Adrienne Raglin, Carl Busart, Timothy Gregory, Anuradha Ravi, Nirmalya Roy
DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models
Chen Qian, Dongrui Liu, Jie Zhang, Yong Liu, Jing Shao