Training large, general-purpose language models poses significant challenges. The growing availability of specialized expert models, fine-tuned from pretrained models for specific tasks or domains, offers a promising alternative. Leveraging the potential of these existing expert models in real-world applications requires effective methods to select or merge the models best suited for a given task. This paper introduces SPECTR, an approach for dynamically composing expert models at each time step during inference. Notably, our method requires no additional training and enables flexible, token- and layer-wise model combinations. Our experimental results demonstrate that SPECTR improves routing accuracy over alternative training-free methods, increasing task performance across expert domains.
@article{arxiv.2504.03454,
title = {SpectR: Dynamically Composing LM Experts with Spectral Routing},
author = {William Fleshman and Benjamin Van Durme},
journal= {arXiv preprint arXiv:2504.03454},
year = {2025}
}