中文大语言模型指令微调的动态特性
Dynamics of Instruction Fine-Tuning for Chinese Large Language Models
AI总结：
本研究系统调查了数据量、模型规模和构建方法对中文大语言模型指令微调的影响，发现不同能力的缩放敏感性可通过复杂性和迁移性解释，定制训练策略能高效提升特定能力及基准性能。
摘要：
指令微调是激发大语言模型（LLMs）通用智能的一种新兴方法。尽管已有大量研究考察了数据量和模型规模等因素对英文模型的影响，但其他语言中指令微调的缩放特性在很大程度上仍未被探索。在本研究中，我们系统地调查了数据量、模型规模和数据构建方法对中文LLMs指令微调的影响。我们使用了一个新整理的数据集DoIT，该数据集包含超过40,000个高质量的指令实例，涵盖十种基础能力，如创意写作、代码生成和逻辑推理。我们在参数规模从7b到33b的模型上进行了实验，得出三个关键发现：(i) 尽管这些因素直接影响模型的整体性能，但某些能力对缩放更为敏感，而另一些则表现出显著的抗性。(ii) 不同能力对这些因素的缩放敏感性可以通过两个特征来解释：复杂性和迁移性。(iii) 通过针对不同敏感性定制训练策略，可以高效地学习特定能力，从而在两个公共基准上提升性能。
英文摘要：
Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models (LLMs). While numerous studies have examined the impact of factors such as data volume and model size on English models, the scaling properties of instruction tuning in other languages remain largely unexplored. In this work, we systematically investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese LLMs. We utilize a newly curated dataset, DoIT, which includes over 40,000 high-quality instruction instances covering ten underlying abilities, such as creative writing, code generation, and logical reasoning. Our experiments, conducted on models ranging from 7b to 33b parameters, yield three key findings: (i) While these factors directly affect overall model performance, some abilities are more responsive to scaling, whereas others demonstrate significant resistance. (ii) The scaling sensitivity of different abilities to these factors can be explained by two features: Complexity and Transference. (iii) By tailoring training strategies to their varying sensitivities, specific abilities can be efficiently learned, enhancing performance on two public benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
