15 papers
Calibrated Counterfactual Conformal Fairness (): Post-hoc, Shift-Aware Coverage Parity via Conformal Prediction and Counterfactual Regularization
Faruk Alpay, Taylan Alpay
We present Calibrated Counterfactual Conformal Fairness (), a post-hoc procedure that targets group-conditional coverage parity under covariate shift. combines importa…
XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols
Faruk Alpay, Taylan Alpay
Structured prompting with XML tags has emerged as an effective way to steer large language models (LLMs) toward parseable, schema-adherent outputs in real-world systems. We develop…
Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions
Faruk Alpay, Taylan Alpay
Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principl…
Nonlinear Continuum of States and Intuitionistic Flows in a Cognitive Space
Faruk Alpay, Taylan Alpay
We construct a rigorous mathematical framework for an abstract continuous evolution of an internal state, inspired by the intuitive notion of a flowing thought sequence. Using tool…
Deterministic Coreset Construction via Adaptive Sensitivity Trimming
Faruk Alpay, Taylan Alpay
We develop a rigorous framework for deterministic coreset construction in empirical risk minimization (ERM). Our central contribution is the Adaptive Deterministic Uniform-Weight T…
Reliability, Embeddedness, and Agency: A Utility-Driven Mathematical Framework for Agent-Centric AI Adoption
Faruk Alpay, Taylan Alpay
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency >…