考虑拟合误差的大语言模型训练数据归因增强方法
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
AI总结:
针对大语言模型训练数据归因中拟合误差损害溯源准确性的问题,本文提出去偏与去噪归因方法DDA,通过消除基础模型知识偏差和平滑拟合差异来增强影响函数,在多个模型上取得91.64%的平均AUC并展现出良好的通用性。
摘要:
大语言模型(LLMs)的黑箱特性给结果解释带来了挑战,影响了数据知识产权保护和幻觉溯源等问题。训练数据归因(TDA)方法被认为是应对这些挑战的有效解决方案。最近的大多数TDA方法依赖于影响函数,并假设模型达到了经验风险最小化。然而,实现这一标准十分困难,并且溯源准确性可能因模型训练过程中的拟合误差而受损。本文提出了一种新颖的TDA方法,称为去偏与去噪归因(Debias and Denoise Attribution,DDA),该方法通过处理拟合误差来增强影响函数。具体而言,去偏策略旨在通过消除微调前基础模型中存在的知识偏差来提升影响函数的性能,而去噪策略则旨在通过平滑技术减少训练过程中因拟合程度不同而产生的影响分数差异。实验结果表明,我们的方法显著优于现有方法,取得了91.64%的平均AUC。此外,DDA在多种数据来源以及LLaMA2、QWEN2和Mistral等不同规模模型上表现出很强的通用性和可扩展性。
英文摘要:
The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered effective solutions to address these challenges. Most recent TDA methods rely on influence functions, assuming the model achieves minimized empirical risk. However, achieving this criterion is difficult, and sourcing accuracy can be compromised by fitting errors during model training. In this paper, we introduce a novel TDA method called Debias and Denoise Attribution (DDA), which enhances influence functions by addressing fitting errors. Specifically, the debias strategy seeks to improve the performance of influence functions by eliminating the knowledge bias present in the base model before fine-tuning, while the denoise strategy aims to reduce discrepancies in influence scores arising from varying degrees of fitting during the training process through smoothing techniques. Experimental results demonstrate that our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. Moreover, DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
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。