5 papers
Reliable Explanations or Random Noise? A Reliability Metric for XAI
Poushali Sengupta, Sabita Maharjan, Frank Eliassen +2
In recent years, explaining decisions made by complex machine learning models has become essential in high-stakes domains such as energy systems, healthcare, finance, and autonomou…
Context Dependence and Reliability in Autoregressive Language Models
Poushali Sengupta, Shashi Raj Pandey, Sabita Maharjan +1
Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history.…
Explainability of Complex AI Models with Correlation Impact Ratio
Poushali Sengupta, Rabindra Khadka, Sabita Maharjan +5
Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Common post hoc AI explainers, such as LIME…
Correlation-Aware Feature Attribution Based Explainable AI
Poushali Sengupta, Yan Zhang, Frank Eliassen +1
Explainable AI (XAI) is increasingly essential as modern models become more complex and high-stakes applications demand transparency, trust, and regulatory compliance. Existing glo…
Privacy-Utility-Fairness: A Balanced Approach to Vehicular-Traffic Management System
Poushali Sengupta, Sabita Maharjan, frank Eliassen +1
Location-based vehicular traffic management faces significant challenges in protecting sensitive geographical data while maintaining utility for traffic management and fairness acr…