Hamman, Faisal

9 publications

NeurIPS 2025 Few-Shot Knowledge Distillation of LLMs with Counterfactual Explanations Faisal Hamman, Pasan Dissanayake, Yanjun Fu, Sanghamitra Dutta

AISTATS 2025 Quantifying Knowledge Distillation Using Partial Information Decomposition Pasan Dissanayake, Faisal Hamman, Barproda Halder, Ilia Sucholutsky, Qiuyi Zhang, Sanghamitra Dutta

ICML 2025 Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs Faisal Hamman, Pasan Dissanayake, Saumitra Mishra, Freddy Lecue, Sanghamitra Dutta

NeurIPS 2025 T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning Yanjun Fu, Faisal Hamman, Sanghamitra Dutta

TMLR 2025 Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition Barproda Halder, Faisal Hamman, Pasan Dissanayake, Qiuyi Zhang, Ilia Sucholutsky, Sanghamitra Dutta

ICLR 2024 Demystifying Local & Global Fairness Trade-Offs in Federated Learning Using Partial Information Decomposition Faisal Hamman, Sanghamitra Dutta

NeurIPSW 2024 Formalizing Limits of Knowledge Distillation Using Partial Information Decomposition Pasan Dissanayake, Faisal Hamman, Barproda Halder, Ilia Sucholutsky, Qiuyi Zhang, Sanghamitra Dutta

ICMLW 2023 Demystifying Local and Global Fairness Trade-Offs in Federated Learning Using Information Theory Faisal Hamman, Sanghamitra Dutta

ICML 2023 Robust Counterfactual Explanations for Neural Networks with Probabilistic Guarantees Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta