对比了大模型文档分类中嵌入与生成方法的优劣，发现生成式模型更准但对数据不均衡敏感。
Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges
- 用思维链提示增强生成式多模态模型，提升零样本分类准确率
- 生成式模型零样本准确率达82%，远超嵌入模型的63%
- 微调虽能提效，但对训练数据不平衡极为敏感
本研究对比分析了用于地球科学文献分类的嵌入式与生成式模型。基于跨学科基准数据集，评估了模型在准确率、稳定性与计算成本间的权衡。结果表明，采用思维链（CoT）提示的生成式视觉-语言模型（如Qwen2.5-VL）在零样本场景下达到82%的准确率，显著优于最先进的多模态嵌入模型QQMM的63%。同时发现，尽管监督微调（SFT）可提升生成式模型性能，但其对训练数据不平衡极为敏感。
原文摘要 · Abstract (English)
This work presents a comparative analysis of embedding-based and generative models for classifying geoscience technical documents. Using a multi-disciplinary benchmark dataset, we evaluated the trade-offs between model accuracy, stability, and computational cost. We find that generative Vision-Language Models (VLMs) like Qwen2.5-VL, enhanced with Chain-of-Thought (CoT) prompting, achieve superior zero-shot accuracy (82%) compared to state-of-the-art multimodal embedding models like QQMM (63%). We also demonstrate that while supervised fine-tuning (SFT) can improve VLM performance, it is sensitive to training data imbalance.
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。