Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915088773939200 |
|---|---|
| author | Freitag, Raquel Meister Ko de Gois, Túlio Sousa |
| author_facet | Freitag, Raquel Meister Ko de Gois, Túlio Sousa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10991 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese Freitag, Raquel Meister Ko de Gois, Túlio Sousa Computation and Language Computers and Society 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. |
| title | Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2410.10991 |