Auditable Agents: Ensuring AI Accountability & Security
Discover how auditable agents enhance AI accountability through action tracking, policy compliance, and tamper-proof evidence for safer deployments.
Detecting Untrustworthy Boundaries in Black-box LLMs
Discover how GMRL-BD detects bias and untrustworthy boundaries in black-box LLMs using bias-diffusion and multi-agent reinforcement learning.
OntoTKGE: Boosting Temporal Knowledge Graph Prediction
OntoTKGE enhances temporal knowledge graph extrapolation by integrating ontological knowledge to improve prediction accuracy and handle sparse data.
Adaptive Serverless Resource Management to Cut Cold Starts
Optimize serverless computing with adaptive resource management, reducing cold start latency and improving cost-efficiency using predictive and event-drive...
Automated Auditing of Hospital Discharge Summaries Using LLMs
Enhance care transitions with automated auditing of hospital discharge summaries using Large Language Models for scalable, accurate clinical documentation.