用纠错机制提升小模型金融分类准确率
Empowering Small Language Models with Factual Hallucination-Aware Reasoning for Financial Classification
- 三步流程：识别关联、自动检测、自适应推理
- 事实幻觉与分类错误正相关，纠正后性能提升
- 适合需要可靠推理的金融场景应用
小语言模型（SLMs）因推理快、可本地部署，被广泛用于金融分类。但相比大模型，其在推理中更易产生事实幻觉，分类性能较弱。本文提出三步流水线AAAI（关联识别、自动检测、自适应推理），在三个代表性SLMs上实验发现：（1）事实幻觉与误分类呈正相关；（2）基于编码器的验证器能有效检测事实幻觉；（3）引入事实错误反馈后，SLMs可实现自适应推理，显著提升分类性能。该方法有助于提升SLMs在金融领域的可信与高效应用。
原文摘要 · Abstract (English)
Small language models (SLMs) are increasingly used for financial classification due to their fast inference and local deployability. However, compared with large language models, SLMs are more prone to factual hallucinations in reasoning and exhibit weaker classification performance. This raises a natural question: Can mitigating factual hallucinations improve SLMs' financial classification? To address this, we propose a three-step pipeline named AAAI (Association Identification, Automated Detection, and Adaptive Inference). Experiments on three representative SLMs reveal that: (1) factual hallucinations are positively correlated with misclassifications; (2) encoder-based verifiers effectively detect factual hallucinations; and (3) incorporating feedback on factual errors enables SLMs' adaptive inference that enhances classification performance. We hope this pipeline contributes to trustworthy and effective applications of SLMs in finance.
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。