Round-trip translation quality in GPT-4 and Llama 2 is jointly shaped by training data volume and language distance from English, with orthographic, phylogenetic, syntactic, and geographic distances as the strongest predictors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Information Loss in LLMs' Multilingual Translation: The Role of Training Data, Language Proximity, and Language Family
Round-trip translation quality in GPT-4 and Llama 2 is jointly shaped by training data volume and language distance from English, with orthographic, phylogenetic, syntactic, and geographic distances as the strongest predictors.