arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.09168cs.CL
收藏

LLM的混合训练方法:利用真实和合成数据提升特定领域应用中的模型性能

Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications

Alexey Zhezherau, Alexei Yanockin

AI总结:

本研究提出一种结合真实与合成数据微调LLMs的混合方法,通过引入合成角色与场景克服真实数据局限,实验证明该混合模型在特定垂直应用中各项指标均优于基线与真实数据微调模型,显著提升了模型的鲁棒性与上下文敏感性。

摘要:

本研究探索了一种通过整合真实世界与合成数据来微调大型语言模型(LLMs)的混合方法,以提升模型性能,特别是在生成准确且符合上下文的响应方面。通过利用结合了转录真实交互与高质量合成会话的数据集,我们旨在克服稀缺、有噪声及特定领域真实数据的局限性。我们采用了合成角色和场景来增强训练的多样性。本研究评估了三个模型:基础模型、用真实数据微调的模型以及混合微调模型。实验结果表明,混合模型在特定垂直应用中始终优于其他模型,在所有指标上均取得最高分。进一步测试证实了混合模型在多样化场景中具有卓越的适应性和上下文理解能力。这些发现表明,结合真实与合成数据可显著提升LLMs的鲁棒性和上下文敏感性,尤其是在特定领域和垂直用例中。

英文摘要:

This research explores a hybrid approach to fine-tuning large language models (LLMs) by integrating real-world and synthetic data to boost model performance, particularly in generating accurate and contextually relevant responses. By leveraging a dataset combining transcribed real interactions with high-quality synthetic sessions, we aimed to overcome the limitations of scarce, noisy, and domain-specific real data. Synthetic personas and scenarios were employed to enhance training diversity. The study evaluated three models: a base foundational model, a model fine-tuned with real data, and a hybrid fine-tuned model. Experimental results showed that the hybrid model consistently outperformed the others in specific vertical applications, achieving the highest scores across all metrics. Further testing confirmed the hybrid model's superior adaptability and contextual understanding across diverse scenarios. These findings suggest that combining real and synthetic data can significantly improve the robustness and contextual sensitivity of LLMs, particularly in domain-specific and vertical use cases.

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。

↑