用检索增强的LLM提升拉丁语依存句法分析，诗歌任务提升17分
THIVLVC: Retrieval Augmented Dependency Parsing for Latin
- 先检索相似句，再用大模型结合示例和规范优化解析结果
- 诗歌任务上比基线提升17点CLAS，散文任务提升1.5点
- 适合处理拉丁语文本，尤其对标注不一致场景有鲁棒性
我们介绍THIVLVC，一种用于EvaLatin 2026依存句法分析任务的两阶段系统。给定拉丁语句子，通过句长和词性n元组相似性从CIRCSE语料库中检索结构相似条目，再利用大语言模型结合检索示例与UD标注规范，对UDPipe生成的初始解析进行优化。提交了两种配置：无检索和带检索（RAG）。在诗歌（塞内加）任务中，THIVLVC相比UDPipe基线提升17点CLAS；在散文（托马斯·阿奎那）任务中，提升1.5点CLAS。对300个系统与标准答案差异的双盲错误分析显示，在一致标注中53.3%倾向支持THIVLVC，揭示了树库内部及跨树库的标注不一致性。
原文摘要 · Abstract (English)
We describe THIVLVC, a two-stage system for the EvaLatin 2026 Dependency Parsing task. Given a Latin sentence, we retrieve structurally similar entries from the CIRCSE treebank using sentence length and POS n-gram similarity, then prompt a large language model to refine the baseline parse from UDPipe using the retrieved examples and UD annotation guidelines. We submit two configurations: one without retrieval and one with retrieval (RAG). On poetry (Seneca), THIVLVC improves CLAS by +17 points over the UDPipe baseline; on prose (Thomas Aquinas), the gain is +1.5 CLAS. A double-blind error analysis of 300 divergences between our system and the gold standard reveals that, among unanimous annotator decisions, 53.3% favour THIVLVC, showing annotation inconsistencies both within and across treebanks.
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。