ARTFEED — Contemporary Art Intelligence

Orthogonal Subspaces Method Improves LoRA Model Merging

ai-technology · 2026-06-01

Researchers have identified a cause of performance degradation when merging large language models fine-tuned with low-rank adaptation (LoRA). They propose Orthogonal Subspaces for Robust Model Merging (OSRM), which constrains the LoRA subspace prior to fine-tuning to prevent task interference. OSRM integrates with existing merging algorithms and was tested on eight datasets.

Key facts

  • Fine-tuning LLMs for individual tasks is expensive for deployment and storage.
  • Model merging combines multiple task-specific models into one multi-task model without additional training.
  • Existing merging methods often fail for models fine-tuned with LoRA due to performance degradation.
  • The issue arises from interplay between model parameters and data distributions.
  • OSRM constrains the LoRA subspace prior to fine-tuning.
  • OSRM reduces unintended interference among tasks.
  • OSRM can integrate with most existing merging algorithms.
  • Experiments were conducted on eight datasets.

Entities

Sources