Epistemic Twins: Enabling a Symbolic Science of Language Model Knowledge
Large Language Models (LLMs) are impactful yet opaque artifacts. At their core, they are subsymbolic constructs defined by billions of numeric weights that interact in a largely inscrutable manner. Current analysis paradigms are either black-box benchmarks that test model performance on pre-defined tasks, or mechanisti...
Simon Razniewski, Shrestha Ghosh, Luca Giordano et al.
· Zenodo (CERN European Organi... · 0 citations