What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations

TitleWhat Do Llamas Really Think? Revealing Preference Biases in Language Model Representations
Publication TypeJournal Article
Year of Publication2023
AuthorsTang, R., X. Zhang, J. Lin, and F. Türe
JournalArXiv
Volumeabs/2311.18812
DOI10.48550/ARXIV.2311.18812