用文献微调大模型，实现可解释的卡车驾驶风险预测。
LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs
- 基于299篇领域论文构建知识库，微调大模型进行风险推理。
- 召回率提升26.7%，F1-score提升10.1%，优于基准模型。
- 能识别高风险变量组合，适合交通安全管理与智能驾驶研究者。
本研究提出一种可解释的卡车驾驶风险预测框架LIFT，结合文献驱动的微调大模型。框架包含三个部分：基于大模型的推理核心、从299篇领域论文自动构建的知识库处理管道，以及评估预测性能与可解释性的结果评价模块。在真实世界卡车驾驶风险数据集上微调后，LIFT大模型在召回率上比基准模型提升26.7%，F1-score提升10.1%。其变量重要性排序与基准模型一致，且在不同采样条件下保持解释鲁棒性。该模型还能通过检测关键变量组合识别潜在高风险场景，并经PERMANOVA检验验证。研究还证明了文献知识库和微调过程对可解释性的贡献，展示了其在数据驱动知识发现中的潜力。
原文摘要 · Abstract (English)
This study proposes an interpretable prediction framework with literature-informed fine-tuned (LIFT) LLMs for truck driving risk prediction. The framework integrates an LLM-driven Inference Core that predicts and explains truck driving risk, a Literature Processing Pipeline that filters and summarizes domain-specific literature into a literature knowledge base, and a Result Evaluator that evaluates the prediction performance as well as the interpretability of the LIFT LLM. After fine-tuning on a real-world truck driving risk dataset, the LIFT LLM achieved accurate risk prediction, outperforming benchmark models by 26.7% in recall and 10.1% in F1-score. Furthermore, guided by the literature knowledge base automatically constructed from 299 domain papers, the LIFT LLM produced variable importance ranking consistent with that derived from the benchmark model, while demonstrating robustness in interpretation results to various data sampling conditions. The LIFT LLM also identified potential risky scenarios by detecting key combination of variables in truck driving risk, which were verified by PERMANOVA tests. Finally, we demonstrated the contribution of the literature knowledge base and the fine-tuning process in the interpretability of the LIFT LLM, and discussed the potential of the LIFT LLM in data-driven knowledge discovery.
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。