Selective deletion of 0.05% of LLM weights achieves fine-tuning-level performance gains
Original article in KoreanAI 모델 가중치 0.05%만 삭제했더니…전체 미세조정 수준 성능 향상
- Outlet
- AI Times
- Published
- Importance
- 3/5
Summary
Researchers from NYU and the University of Calgary reported that selectively removing less than 0.05% of an LLM's weights without retraining other parameters significantly improves math reasoning and tool-use capabilities. The method achieves performance comparable to full fine-tuning while reducing storage requirements and preserving existing capabilities.