שיפור של דגלי שפה גדולים באמצעות תלת-קווי תלוי-מסכה

תקציר מקורי באנגליתarXiv:2503.22764v3 Announce Type: replace-cross Abstract: The large language model (LLM) is typically integrated into the mainstream optimization protocol. However, it remains underexplored whether maintaining the model integrity is \textit{indispensable} for promising performance. In this work, we introduce Mask Fine-Tuning (MFT), a novel LLM fine-tuning paradigm demonstrating that carefully breaking the model's structural integrity can surprisingly improve performance without updating model weights. MFT learns and applies binary masks to well-optimized models, using the standard LLM fine-tuning objective as supervision. Based on fully fine-tuned models, MFT uses the same fine-tuning datasets to achieve consistent performance gains across domains and backbones (e.g., an average gain of 2.