Jul 2026
Verbalizable Representations Form a Global Workspace in Language Models
Evidence that an analogous functional distinction has emerged in large language models is presented, showing that language models maintain a small, privileged set of representations bearing some of the functional hallmarks of conscious access, and that decoding these representations sheds light on ongoing cognitive processes.
Wes Gurnee, Nicholas J. Sofroniew, Adam Pearce et al.
· arXiv.org · 40 citations
· ⚡6