Same question, different history: language, national identity, and credit in large language models
2026-06-22 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how big language models answer questions about who invented certain important things, like the radio or telephone. They found that the language used to ask the question influences which inventor the models mention, often favoring inventors connected to that language's culture. Even though the models know that these inventions have disputed origins, they tend to show different national stories depending on the language. This suggests that these language models reflect cultural memories linked to language, shaping which historical facts are highlighted.
large language modelscultural memorydisputed inventionslanguage biasnational narrativesAnglophone dominancehistorical memorymultilingual evaluationcomputational nationalism
Authors
William Guey, Pierrick Bougault, Wei Zhang, Vitor D. de Moura, José O. Gomes
Abstract
Who invented the radio, Russia's Alexander Popov or Italy's Guglielmo Marconi? Was the telephone the achievement of Bell in the United States or Meucci in Italy? Does printing belong to China's Bi Sheng or Germany's Gutenberg? The answer depends not only on historical record but also on language and perspective. We analyse eleven widely used large language models across 21 disputed inventions and discoveries, evaluated in twelve languages and 75,896 responses. While models generally acknowledge that credit is contested, query language systematically affects which claimant is surfaced. Lower-status claimants are more likely to appear when questions are asked in their associated language, whereas dominant Anglophone figures remain stable across languages. These patterns persist after controlling for response length, model differences, historical prominence, and levels of national commemoration. Language thus acts as a switch that activates different national versions of the same history, producing systematically different national memories from the same question. We interpret this as evidence that large language models function as distributed systems of cultural memory, where language conditions which histories become visible, contributing to a computational form of banal nationalism.