arXiv:2506.10885cs.CLcs.AI2025-06

用高效微调让大模型变小,性能不降反而提升

Slimming Down LLMs Without Losing Their Minds

  • 用LoRA/QLoRA等方法实现参数高效微调
  • 在常识、数学、知识三领域表现显著提升
  • 适合资源有限却想快速适配大模型的开发者

本文研究并验证了微调对大语言模型性能的影响,聚焦于参数高效方法(LoRA和QLoRA)。我们在三个关键领域评估模型能力:(1) 常识推理(HellaSwag),(2) 数学推理(GSM8K),(3) 多领域知识(MMLU-CS)。研究发现:(1) 基于LoRA的方法能有效提升任务特定性能,同时保持计算效率;(2) 性能强弱高度依赖微调数据集与评测任务的一致性。该研究为参数高效机制提供了理论见解,并为资源受限的开发者提供了实用指导。

原文摘要 · Abstract (English)

This paper investigates and validates the impact of fine-tuning on large language model performance, focusing on parameter-efficient methods (LoRA and QLoRA). We evaluate model capabilities across three key domains: (1) commonsense reasoning (HellaSwag), (2) mathematical reasoning (GSM8K), and (3) multi-domain knowledge (MMLU-CS). Our findings demonstrate that: (1) LoRA-based methods effectively improve task-specific performance while maintaining computational efficiency, and (2) performance strongly depends on alignment between fine-tuning dataset and benchmark tasks. The study provides both theoretical insights into parameter-efficient mechanisms and practical guidance for developers implementing efficient LLM adaptation with limited resources.

大模型压缩微调优化参数高效

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。