4 papers
First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers
Irina Piontkovskaia, Sergey Nikolenko
Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint,…
Recoverable but Not Stationary:Local Linear Structures in Weights and Activations
Irina Piontkovskaia, Sergey Nikolenko
Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear directions. We ask which linear…
MindFuse: Towards GenAI Explainability in Marketing Strategy Co-Creation
Aleksandr Farseev, Marlo Ongpin, Qi Yang +3
The future of digital marketing lies in the convergence of human creativity and generative AI, where insight, strategy, and storytelling are co-authored by intelligent systems. We…
SOMONITOR: Combining Explainable AI & Large Language Models for Marketing Analytics
Aleksandr Farseev, Qi Yang, Marlo Ongpin +3
Online marketing faces formidable challenges in managing and interpreting immense volumes of data necessary for competitor analysis, content research, and strategic branding. It is…