Glossary-augmented LLM prompting reaches 81.4% terminology accuracy on rock art documents versus 69.1% for basic LLM and 64.4% for DeepL, with no loss in overall quality scores.
InA Cognitive Linguistics View of Terminology and Spe- cialized Language, pages 9–31
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents
Glossary-augmented LLM prompting reaches 81.4% terminology accuracy on rock art documents versus 69.1% for basic LLM and 64.4% for DeepL, with no loss in overall quality scores.