THIVLVC: Retrieval Augmented Dependency Parsing for Latin
On the map: Retrieval-augmented generation → Generation and context integration
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 1 of its 6 references that are in the map. First posted on arXiv 7 Apr 2026.
Builds on
1 of 6 references.
References · 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
- 2025"Don't Teach Minerva": Guiding LLMs Through Complex Syntax for Faithful Latin Translation with RAG
- 2024R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models
- 2025Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing
- 2022Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing
- 2026LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian
- 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing
- 2025U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack