SpectR: Dynamically Composing LM Experts with Spectral Routing

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{fleshman2025_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 }
}