ResMerge improves merging of RL expert LLMs via a stable residual consensus backbone plus gated head correction, outperforming task-vector and spectral baselines in capability preservation.
arXiv preprint arXiv:2412.00081 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.
citing papers explorer
-
ResMerge: Residual-based Spectral Merging of Large Language Models
ResMerge improves merging of RL expert LLMs via a stable residual consensus backbone plus gated head correction, outperforming task-vector and spectral baselines in capability preservation.
-
One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging
Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.
- Training-free Task Classification for Multi-Task Model Merging