Topic
explainability
JustDiag! Diagnostic Justification Engine Enhances Accountability in Root Cause Analysis
JustDiag! is a diagnostic justification engine for root cause analysis that maintains an explicit process state over evidence, findings, competing hypotheses, conflicts, and next checks. Evaluated on 66 real-world incidents, it achieved stronger outcome and process scores compared to a control without diagnostic justification, though with slightly lower terminal completion due to calibrated non-closure.
TelcoAgent: Foundation Model-Based Framework for Scalable and Explainable 5G KPM Forecasting
TelcoAgent is a foundation model-based framework for 5G key performance measurement forecasting that addresses scalability and explainability issues. It uses a 3GPP knowledge graph and time-series foundation model to deliver zero-shot predictions across multiple cells. Evaluated on a real-world city-scale 5G dataset from a U.S. operator, it achieved high accuracy for seven KPMs per cell across 200 cells.
Beyond Accuracy: New Metric Measures Logical Compliance of Predictive Models for Enterprise AI
Researchers introduce the Rule Violation Score (RVS), a complementary evaluation metric that measures how well predictive models adhere to predefined logical rules, independent of accuracy. Tests on knowledge graph and regression benchmarks show models with similar accuracy can differ significantly in logical compliance.
New Definition of Good Explanations Highlights Challenges in Explaining LLM Outputs
A recent arXiv paper by Mahon, Louis, Ford, Elliot, Hackett, and Callum proposes a definition of good explanations inspired by counterfactual explanations but incorporating the interlocutor's prior beliefs. The authors explore the ramifications for AI explainability, particularly why LLM outputs are difficult to explain well.