Papers by Gerson Vizcarra
In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Multilingual generative language models (LMs) are fluent in a large variety of languages. |
| Approach: | They analyze formality distributions of XGLM and BLOOM’s predictions in 5 languages and classify 1,200 generations per language as formal, informal, or incohesive. |
| Outcome: | The proposed models generate a significant amount of informal predictions even when prompted with formal text. |