activity
20212026
collaborators

5 papers

cs.LG2026

Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learning

Malavika Suresh, Ikechukwu Nkisi-Orji, Nirmalie Wiratunga

Achieving continual learning (CL) with deep neural networks requires balancing stability and plasticity while enabling knowledge transfer. In this work, we focus on offline learnin…

cs.IR2026

RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification

Lasal Jayawardena, Nirmalie Wiratunga, Ikechukwu Nkisi-Orji +1

Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affec…

cs.CL2025

Cross-Layer Attention Probing for Fine-Grained Hallucination Detection

Malavika Suresh, Rahaf Aljundi, Ikechukwu Nkisi-Orji +1

With the large-scale adoption of Large Language Models (LLMs) in various applications, there is a growing reliability concern due to their tendency to generate inaccurate text, i.e…

cs.AI2024

iSee: Advancing Multi-Shot Explainable AI Using Case-based Recommendations

Anjana Wijekoon, Nirmalie Wiratunga, David Corsar +7

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the dive…

cs.LG2021

DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods

Nirmalie Wiratunga, Anjana Wijekoon, Ikechukwu Nkisi-Orji +3

Counterfactual explanations focus on "actionable knowledge" to help end-users understand how a machine learning outcome could be changed to a more desirable outcome. For this purpo…