Publications tagged "nlp"
-
PreprintarXiv preprint arXiv:2602.00628 2026We investigate the extent to which an LLM’s hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer models, we run two experimental paradigms – similarity-based forced choice and free association – over a shared 5,000-word vocabulary, collecting 17.5M+ trials to build behavior-based similarity matrices. Using representational similarity analysis, we compare behavioral geometries to layerwise hidden-state similarity and benchmark against FastText, BERT, and cross-model consensus. We find that forced-choice behavior aligns substantially more with hidden-state geometry than free association. In a held-out-words regression, behavioral similarity (especially forced choice) predicts unseen hidden-state similarities beyond lexical baselines and cross-model consensus, indicating that behavior-only measurements retain recoverable information about internal semantic geometry. Finally, we discuss implications for the ability of behavioral tasks to uncover hidden cognitive states.
@article{schiekiera2026associations, title = {From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs}, author = {Schiekiera, Louis and Zimmer, Max and Roux, Christophe and Pokutta, Sebastian and G{\"u}nther, Fritz}, journal = {arXiv preprint arXiv:2602.00628}, year = {2026}, }