用动态提示与知识增强提升铁路术语消歧准确率
DACE For Railway Acronym Disambiguation
- 动态调整提示词以应对不同歧义程度的缩写
- 在法语铁路文档上取得0.9069的F1分数
- 适合低资源场景下的技术文本处理
缩写消歧是技术文本处理中的基础挑战，尤其在高歧义的专有领域中会阻碍自动化分析。本文针对TextMine'26法国铁路文档竞赛提出DACE框架——结合动态提示、检索增强生成、上下文选择与集成聚合，通过自适应上下文学习和外部领域知识注入，增强大语言模型性能。该方法通过动态优化提示并集成多模型预测，有效缓解幻觉问题，在低资源场景下表现优异。最终在竞赛中获得第一名，F1得分为0.9069。
原文摘要 · Abstract (English)
Acronym Disambiguation (AD) is a fundamental challenge in technical text processing, particularly in specialized sectors where high ambiguity complicates automated analysis. This paper addresses AD within the context of the TextMine'26 competition on French railway documentation. We present DACE (Dynamic Prompting, Retrieval Augmented Generation, Contextual Selection, and Ensemble Aggregation), a framework that enhances Large Language Models through adaptive in-context learning and external domain knowledge injection. By dynamically tailoring prompts to acronym ambiguity and aggregating ensemble predictions, DACE mitigates hallucination and effectively handles low-resource scenarios. Our approach secured the top rank in the competition with an F1 score of 0.9069.
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。