Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese

Autor:	Freitag, Raquel Meister Ko, de Gois, Túlio Sousa
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Computers and Society
Druh dokumentu:	Working Paper
Popis:	Different of biases are reproduced in LLM-generated responses, including dialectal biases. A study based on prompt engineering was carried out to uncover how LLMs discriminate varieties of Brazilian Portuguese, specifically if sociolinguistic rules are taken into account in four LLMs: GPT 3.5, GPT-4o, Gemini, and Sabi.-2. The results offer sociolinguistic contributions for an equity fluent NLP technology. Comment: 8 pages, XI Jornada de Descri\c{c}\~ao do Portugu\^es
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.10991 Zobrazit plný text záznamu View this record from Arxiv