3 papers
cs.NI2026
CENTILE: A Telemetry Foundation Model Evaluated by the Decisions It Drives
Zifan Zhang, Zhichao Hou, Tingxiang Ji +1
Modern computing and networking infrastructure emits telemetry continuously, yet operators convert it into decisions with a separate predictor per task, entity, and horizon. One ge…
cs.CL2026
LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
Zipeng Ling, Shuliang Liu, Yuehao Tang +7
Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misused: in real-world applications,…
cs.LG2024
Post-hoc Interpretability Illumination for Scientific Interaction Discovery
Ling Zhang, Zhichao Hou, Tingxiang Ji +2
Model interpretability and explainability have garnered substantial attention in recent years, particularly in decision-making applications. However, existing interpretability tool…