Mapping Meaning in Latin with Large Language Models:A Multi-Task Evaluation of Preverbed Motion Verbs and Spatial Relation Detection in LLMs

This paper evaluates the capabilities of Large Language Models (LLMs) on three interrelated linguistic tasks in Latin: preverbed motion verb identification, spatial relation (SR) classification, and SR type disambiguation. We evaluate GPT-4, Llama, and Mistral under zero-shot and few-shot settings, using a manually annotated dataset of Latin sentences drawn from different authors, text types, and historical periods (3rd century BCE – 2nd century CE) as our gold standard. Results show that GPT-4 consistently outperforms open-weight models, particularly in zero-shot scenarios, likely due to its substantial pretraining exposure to Latin. However, even GPT-4 struggles with syntactic disambiguation, especially in linking proper nouns to their governing verbs. SR classification performance is skewed by dataset imbalance, and SR type disambiguation errors often stem from over-reliance on salience over syntax. Qualitative analysis reveals common patterns of overgeneration and uncertainty across tasks. Our findings underscore the potential of LLMs for historical language processing while highlighting persistent challenges related to ambiguity, entity linking, and syntactic reasoning. This study represents the first evaluation of SR recognition in historical languages and lays the groundwork for future domain-adapted fine-tuning approaches in Computational Humanities.