Which Decisions Low-Bit Quantization Breaks, and How to Predict Them
量化损伤是乘法性的,而非加法性的
机构 * Holistic AI(霍利斯提克人工智能公司) ; University College London(伦敦大学学院)
AI总结 该研究发现大型语言模型的量化损伤是乘法性的,而非加法性的,提出边际收缩概念,拟合关系可准确预测决策翻转率,增加1位是修复损伤最廉价的方式。
Comments 18 pages, 9 figures, 8 tables. Under review at the Third Workshop on Uncertainty-Aware NLP (UncertaiNLP), EMNLP 2026 (non-archival)