Finding the Plea: Evaluating the Ability of LLMs to Identify Rhetorical Structure in Swedish and English Historical Petitions

Ellinor Lindqvist, Eva Pettersson, Joakim Nivre


Abstract
Large language models (LLMs) have shown impressive capabilities across many NLP tasks, but their effectiveness on fine-grained content annotation, especially for historical texts, remains underexplored. This study investigates how well GPT-4, Gemini, Mixtral, Mistral, and LLaMA can identify rhetorical sections (Salutatio, Petitio, and Conclusio) in 100 English and 100 Swedish petitions using few-shot prompting with varying levels of detail. Most models perform very well, achieving F1 scores in the high 90s for Salutatio, though Petitio and Conclusio prove more challenging, particularly for smaller models and Swedish data. Cross-lingual prompting yields mixed results, and models generally underestimate document difficulty. These findings demonstrate the strong potential of LLMs for assisting with nuanced historical annotation while highlighting areas for further investigation.
Anthology ID:
2025.lm4dh-1.8
Volume:
Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Isuri Nanomi Arachchige, Francesca Frontini, Ruslan Mitkov, Paul Rayson
Venues:
LM4DH | WS
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
86–101
Language:
URL:
https://aclanthology.org/2025.lm4dh-1.8/
DOI:
Bibkey:
Cite (ACL):
Ellinor Lindqvist, Eva Pettersson, and Joakim Nivre. 2025. Finding the Plea: Evaluating the Ability of LLMs to Identify Rhetorical Structure in Swedish and English Historical Petitions. In Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities, pages 86–101, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Finding the Plea: Evaluating the Ability of LLMs to Identify Rhetorical Structure in Swedish and English Historical Petitions (Lindqvist et al., LM4DH 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.lm4dh-1.8.pdf