Re:Generative AI uses more energy on non-English text
by pama on Saturday November 14, 2026 @10:37AM
(#50497854)
Thanks for this table! Do you happen to have the fraction of accepted speculative decoding outputs as well? I know it is asking much, but do you possibly measure differences in different across speculation techniques (dspark vs dflash) and differences in framework/code used (unless you only use in house code for these and cannot run sglang or vllm)? Your table is more interesting than the blog for sure.
Re:Generative AI uses more energy on non-English text
by scottcha on Saturday November 14, 2026 @11:05AM
(#50498111)
We do use spec decode on all these models (I don't know if the paper is using that but I'm assuming not given the models listed) but not all these models have integrated spec decode stats in the responses. Turns out GLM 5.3 does though so here is a pass on that model.
Language Accept Tokens/step 0/3 steps 3/3 steps Output tok/req
English 76.53% 3.296 9.4% 62.8% 549
Chinese 73.37% 3.201 11.3% 58.2% 754
Russian 73.88% 3.217 11.1% 58.5% 739
French 75.50% 3.265 9.8% 60.9% 631
S. Pashto 70.44% 3.113 12.9% 54.5% 1332
Tigrinya 79.72% 3.391 8.2% 67.8% 3643
Shan 75.64% 3.269 11.2% 63.0% 3675
Tibetan 74.67% 3.240 10.3% 60.2% 2857
Overall 75.75% 3.273 10.3% 62.2% 1772
Re:Generative AI uses more energy on non-English text
by pama on Saturday November 14, 2026 @11:21AM
(#50498240)
Thanks. So the acceptance rates are rather similar across languages.
Re:Generative AI uses more energy on non-English text
by scottcha on Saturday November 14, 2026 @11:30AM
(#50498306)
Yes it looks that way. I pulled the energy data for GLM 5.3 as well just to check the core findings are roughly the same and they do seem to be so spec decode doesn't seem to have the same divergence as the prefill/decode energy (which is rougly a function of thinking/decode lenghts and less a property of individual tokens).
Language Strict Lenient Cap Tok/req J/req J/tok Req x EN Tok x EN J/tok x EN
English 100% 100% 0 548.7 230.33 0.4198 1.00 1.00 1.00
Chinese 96% 96% 1 754.0 694.47 0.9210 3.02 1.37 2.19
Russian 96% 98% 2 738.8 592.15 0.8015 2.57 1.35 1.91
French 100% 100% 0 631.0 1101.84 1.7462 4.78 1.15 4.16
S. Pashto 88% 98% 6 1332.1 208.06 0.1562 0.90 2.43 0.37
Tigrinya 56% 62% 19 3642.9 1445.84 0.3969 6.28 6.64 0.95
Shan 44% 54% 27 3674.8 3791.59 1.0318 16.46 6.70 2.46
Tibetan 2% 70% 15 2856.9 5306.68 1.8575 23.04 5.21 4.42
Re:Generative AI uses more energy on non-English text
by vova_hn2 on Saturday November 14, 2026 @12:18PM
(#50498734)
I think that the fact that TFA doesn't mention speculative decoding at all is not a good sign. It casts doubt both on the accuracy of the data and on the competence of whoever collected it.
I can imagine that in some cases the acceptance rate for non-English responses may be much higher, because while words on average need more tokens to spell, it is more "obvious" what the next token should be, so it is easier for the speculation model to predict it accurately. Information density per token is lower.
Or, maybe the acceptance rate is much lower, if the speculation model is tuned for English and doesn't work well with other languages.
Re:Generative AI uses more energy on non-English text
by scottcha on Saturday November 14, 2026 @10:39AM
(#50497873)
I actually think beyond the large increase in energy noted in the paper the decrease in energy for Russian and Chinese was a bit unexpected. I would have actually expected the Chinese DBCS to use more energy but at least for Chinese there could be a training impact here given these are Chinese models.
Accuracy uses the paper's strict "#### N" parser and lenient fallback. acc is strict/lenient percent. len_cap is the number of responses truncated at the generation-length limit, not an energy cap. Each language has 50 responses.
Across the four low-resource versus four high-resource languages: