collaborators

8 papers

cs.LG2025

T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning

Yanjun Fu, Faisal Hamman, Sanghamitra Dutta

Instruction tuning is essential for Large Language Models (LLMs) to effectively follow user instructions. To improve training efficiency and reduce data redundancy, recent works us…

cs.LG2025

Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition

Barproda Halder, Faisal Hamman, Pasan Dissanayake +3

Spuriousness arises when there is an association between two or more variables in a dataset that are not causally related. In this work, we propose an explainability framework to p…

cs.LG2025

Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations

Faisal Hamman, Pasan Dissanayake, Yanjun Fu +1

Knowledge distillation is a promising approach to transfer capabilities from complex teacher models to smaller, resource-efficient student models that can be deployed easily, parti…

cs.CL2025

Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards

Faisal Hamman, Chenyang Zhu, Anoop Kumar +4

RAG systems are increasingly deployed in high-stakes domains where users expect outputs to be consistent across semantically equivalent queries. However, existing systems often exh…

cs.LG2025

Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs

Faisal Hamman, Pasan Dissanayake, Saumitra Mishra +2

Fine-tuning LLMs on tabular classification tasks can lead to the phenomenon of fine-tuning multiplicity where equally well-performing models make conflicting predictions on the sam…

stat.ML2025

Quantifying Knowledge Distillation Using Partial Information Decomposition

Pasan Dissanayake, Faisal Hamman, Barproda Halder +3

Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a com…