Study Finds Consistent Subjective Preferences in Large Language Model Responses
A new arXiv paper examines how large language models answer subjective questions, reporting regularities such as the bouba/kiki effect in their stated preferences.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv cs.CL
Bouba Beats Kiki, and Other Regularities in the Subjective Preferences of LLMs