DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging

Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training.

Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the merged model's hidden states and those of each individual…