THIVLVC improves Latin dependency parsing via retrieval from a treebank and LLM refinement of UDPipe outputs, gaining +17 CLAS on Seneca poetry and +1.5 on Aquinas prose.
THIVLVC: Retrieval Augmented Dependency Parsing for Latin
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
THIVLVC: Retrieval Augmented Dependency Parsing for Latin
THIVLVC improves Latin dependency parsing via retrieval from a treebank and LLM refinement of UDPipe outputs, gaining +17 CLAS on Seneca poetry and +1.5 on Aquinas prose.