works on
dataset creation 1large language models 1political bias 1societal issues 1stance detection 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CL2026

Are LLMs ready for HardChoices?

Dmitry Nikolaev

The paper investigates whether large language models hold consistent positions on contentious societal issues using a new HardChoices dataset, finding that models rarely stay neutr…