Aryo Pradipta Gema

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains

Noiser: Bounded Input Perturbations for Attributing Large Language Models

Balancing Act: Diversity and Consistency in Large Language Model Ensembles

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations