Linear Interpolation In Parameter Space is Good Enough for Fine-Tuned Language Models
Computation and Language
2022-11-23 v1 Machine Learning
Abstract
The simplest way to obtain continuous interpolation between two points in high dimensional space is to draw a line between them. While previous works focused on the general connectivity between model parameters, we explored linear interpolation for parameters of pre-trained models after fine-tuning. Surprisingly, we could perform linear interpolation without a performance drop in intermediate points for fine-tuned models. For controllable text generation, such interpolation could be seen as moving a model towards or against the desired text attribute (e.g., positive sentiment), which could be used as grounds for further methods for controllable text generation without inference speed overhead.
Cite
@article{arxiv.2211.12092,
title = {Linear Interpolation In Parameter Space is Good Enough for Fine-Tuned Language Models},
author = {Mark Rofin and Nikita Balagansky and Daniil Gavrilov},
journal= {arXiv preprint arXiv:2211.12092},
year = {2022}
}