9 papers
Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming
Zirong Chen, Meiyi Ma
Chain-of-thought (CoT) prompting enables large language models (LLMs) to tackle multi-step reasoning tasks, yet the generated intermediate steps are not guaranteed to be logically…
PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker Training
Zirong Chen, Hongchao Zhang, Meiyi Ma
9-1-1 call-taking training requires mastery of over a thousand interdependent skills, covering diverse incident types and protocol-specific nuances. A nationwide labor shortage is…
Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learned
Zirong Chen, Meiyi Ma
Emergency call-takers form the first operational link in public safety response, handling over 240 million calls annually while facing a sustained training crisis: staffing shortag…
Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection
Yilin Liu, Hongchao Zhang, Taylor T. Johnson +2
Graph anomaly detection methods aim to distinguish anomalous nodes. While prior methods characterize anomalies through increased variation in the spectral energy distributions, the…
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
Hanchen David Wang, Clayton Cohn, Zifan Xu +3
Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing p…
Identifying Adversary Characteristics from an Observed Attack
Soyon Choi, Scott Alfeld, Meiyi Ma
When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization)…