Multilingual LLM inference energy costs vary up to 179x across languages due to script complexity and token counts, with a double penalty on performance for high-energy languages.
In Proceedings of the 31st International Conference on Computational Linguistics, pages 5987–5996, Abu Dhabi, UAE
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
-
The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference
Multilingual LLM inference energy costs vary up to 179x across languages due to script complexity and token counts, with a double penalty on performance for high-energy languages.