Pasan Dissanayake

Distilling Transformers into Neural Nets for Few-Shot Tabular Classification

Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations

Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs

Formalizing Spuriousness of Biased Datasets using Partial Information Decomposition

Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs