Prompt-oriented Output of Culture-Specific Items in Translated African Poetry by Large Language Model: An Initial Multi-layered Tabular Review

TL;DR

This study evaluates how well a large language model translates culture-specific items in African poetry, revealing limitations and inconsistencies in its cultural translation capabilities compared to human and custom engine translations.

Contribution

It provides a multi-layered analysis of LLM outputs for cultural translation in African poetry, highlighting the limited impact of culture-specific prompts.

Findings

LLM did not significantly improve cultural translation with prompts

Humans and custom engines produced more consistent cultural items

LLM showed inconsistencies in translating African cultural elements

Abstract

This paper examines the output of cultural items generated by Chat Generative PreTrained Transformer Pro in response to three structured prompts to translate three anthologies of African poetry. The first prompt was broad, the second focused on poetic structure, and the third prompt emphasized cultural specificity. To support this analysis, four comparative tables were created. The first table presents the results of the cultural items produced after the three prompts, the second categorizes these outputs based on Aixela framework of Proper nouns and Common expressions, the third table summarizes the cultural items generated by human translators, a custom translation engine, and a Large Language Model. The final table outlines the strategies employed by Chat Generative PreTrained Transformer Pro following the culture specific prompt. Compared to the outputs of cultural items from reference human translation and the custom translation engine in prior studies the findings indicate that the culture oriented prompts used with Chat Generative PreTrained Transformer Pro did not yield significant enhancements of cultural items during the translation of African poetry from English to French. Among the fifty four cultural items, the human translation produced thirty three cultural items in repetition, the custom translation engine generated Thirty eight cultural items in repetition while Chat Generative PreTrained Transformer Pro produced forty one cultural items in repetition. The untranslated cultural items revealed inconsistencies in Large language models approach to translating cultural items in African poetry from English to French.