Explaining and Predicting Fine-Tuning in Large Models via Linearization

Zahra Rahimi Afzal, Tara Esmaeilbeig, Mojtaba Soltanalian, Mesrob I. Ohannessian

Published: 22 Sept 2025, Last Modified: 03 Jan 2026WiML @ NeurIPS 2025EveryoneRevisionsBibTeXCC BY 4.0
Keywords: Parameter-Efficient Fine-tuning, LLMs, Neural Tangent Kernel, Linearization, Low Rank Adaptation
Submission Number: 365