projects

mostly the thesis these days: where refusal lives inside llms. the older ml projects moved down to earlier work, they had their time.

01

refusal geometry in llms

msc thesis at sabanci: how refusal and harmfulness live in the internal geometry of llms. ask a model something harmful and it refuses, that refusal can be shown as a direction in activation space, and jailbreaks work by pushing the model off it. i am mapping what those attacks actually do to the representations, no public repo yet, we will see where it goes.

Mechanistic InterpretabilityRefusal DirectionsLLM Safety

earlier work

02

Neural Text Summarization: Comparative Analysis of Transformer Architectures

Comparative study of BART and T5 architectures for automated news summarization, including sentiment-aware evaluation and ROUGE-based benchmarking.

TransformersBARTT5NLTKSentiment AnalysisROUGE Evaluation
03

Multi-Label Classification System for Financial Recommendations

Built a multi-label recommendation system for Isbank using one-vs-all XGBoost with feature engineering and ensemble strategies for improved predictive performance.

XGBoostMulti-Label ClassificationFeature EngineeringFinancial AnalyticsKaggle
04

Machine Learning Algorithm Implementations

Collection of practical machine learning implementations, including boosting, ensemble techniques, and feature engineering workflows applied to real-world datasets.

XGBoostEnsemble MethodsFeature EngineeringData ScienceAlgorithm Implementation