A broad measurement study shows that false refusals in LLMs depend more on model and task choice than on sociodemographic personas, with newer models refusing far less.
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
-
No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models
A broad measurement study shows that false refusals in LLMs depend more on model and task choice than on sociodemographic personas, with newer models refusing far less.