Across 17 sensitive topics and six languages, large language models produce significantly different refusal rates and answer distributions depending on the language used, with the pattern varying by model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models
Across 17 sensitive topics and six languages, large language models produce significantly different refusal rates and answer distributions depending on the language used, with the pattern varying by model.