Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias Itay Itzhak author Gabriel Stanovsky author Nir Rosenfeld author Yonatan Belinkov author 2024 text journal article Transactions of the Association for Computational Linguistics continuing MIT Press Cambridge, MA periodical academic journal itzhak-etal-2024-instructed 10.1162/tacl_a_00673 https://aclanthology.org/2024.tacl-1.43/ 2024 12 771 785