发表机构
Pusan National University; CyberLogitec（釜山国立大学; 赛博洛吉泰克）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出TRIE-HSA方法，结合前缀树约束的令牌预测与层级感知语义对齐，在集装箱码头数据实验中，其HS6准确率较零样本推理提升49.96个百分点，为受限环境下的HS编码预测提供实用方案。
AI 中文摘要
从商品文本中预测协调制度（HS）编码（HSP）对国际贸易至关重要，在港口物流中的重要性持续提升。为此，近期研究人员积极探索大型语言模型（LLM），尤其是因其强大的语言理解能力。但LLM的高计算成本限制了其在集装箱码头等受限环境中的部署。小型语言模型（SLM）是实用替代方案，但其规模较小，易生成无效HS编码，且会忽略商品文本与HS编码间的层级语义。为解决这些局限，本研究提出TRIE-HSA，它结合前缀树约束的令牌预测与层级感知语义对齐（HSA）。该方法约束SLM仅预测HS分类下的有效数字，并将商品文本表示与HS编码的层级结构对齐。在从运营集装箱码头收集的数据上开展的大量实验显示，TRIE-HSA较零样本推理将平均HS6准确率提升49.96个百分点，且比最强的任务特定基准超出11.94个百分点。这些结果表明，采用参数少于100亿的模型即可实现准确且结构有效的HSP。因此，TRIE-HSA为无法支持大型LLM的港口物流运营中的HSP部署提供了实用基础。
英文摘要
Harmonized System (HS) code prediction (HSP) from commodity text is essential to international trade, and its importance continues to grow in port logistics. Recently, large language models (LLMs) have been actively investigated for this task, owing especially to their strong language-understanding capabilities. However, their high computational cost limits deployment in constrained environments such as container terminals. Small language models (SLMs) offer a practical alternative, but their smaller scale makes them prone to generating invalid HS codes and to overlooking the hierarchical semantics between commodity text and HS codes. To address these limitations, this study proposes TRIE-HSA, which combines trie-constrained token prediction with hierarchy-aware semantic alignment (HSA). This framework constrains the SLM to predict only valid digits under the HS taxonomy and aligns commodity text representations with the hierarchical structure of HS codes. In extensive experiments on data collected from an operational container terminal, TRIE-HSA improved average HS6 accuracy by 49.96% over zero-shot inference and exceeded the strongest task-specific benchmark by 11.94%. These results demonstrate that accurate and structurally valid HSP is achievable with fewer than 10 billion parameters. Therefore, TRIE-HSA offers a practical basis for deployment of HSP in port logistics operations that cannot support large scale LLMs.
