FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

Rohan Deb; Kiran Koshy Thekumparampil; Kousha Kalantari; Gaurush Hiranandani; Shoham Sabach; Branislav Kveton

2025 ICML ICML 2025

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Rohan Deb, Kiran Koshy Thekumparampil, Kousha Kalantari, Gaurush Hiranandani, Shoham Sabach, Branislav Kveton

Topics

Machine Learning > Optimization & Theory > Optimization Machine Learning > Application Areas > Domain Adaptation Artificial Intelligence > Core AI > Large Language Models

Keywords

domain adaptation fisher information matrix information gain supervised fine-tuning large language model linearization

Download PDF