基于Mistral的金融信贷大模型，有效减少幻觉提升准确率
ZiGong 1.0: A Large Language Model for Financial Credit
- 用代理模型筛选训练数据，降低金融场景幻觉
- 在真实金融场景中预测准确率显著提升
- 适合需要高可靠性的金融信贷应用开发者
大型语言模型（LLMs）在通用自然语言处理任务中表现优异，但在金融信贷评估中的效果仍不理想，主要因该领域需专业知识。为此，我们提出ZiGong，一个基于Mistral的模型，通过多任务监督微调增强。为应对金融场景中的模型幻觉，引入新型数据清洗方法：利用代理模型对训练样本打分，再将筛选后的数据与原始数据结合用于训练。该数据优化策略有效降低了幻觉，同时保持下游金融应用的可靠性。实验表明，该方法显著提升了模型在真实金融场景中的鲁棒性和预测准确性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated strong performance across various general Natural Language Processing (NLP) tasks. However, their effectiveness in financial credit assessment applications remains suboptimal, primarily due to the specialized financial expertise required for these tasks. To address this limitation, we propose ZiGong, a Mistral-based model enhanced through multi-task supervised fine-tuning. To specifically combat model hallucination in financial contexts, we introduce a novel data pruning methodology. Our approach utilizes a proxy model to score training samples, subsequently combining filtered data with original datasets for model training. This data refinement strategy effectively reduces hallucinations in LLMs while maintaining reliability in downstream financial applications. Experimental results show our method significantly enhances model robustness and prediction accuracy in real-world financial scenarios.
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。