Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions
A novel framework to align MLLMs with the multidimensional mental representations underlying human similarity judgements, which builds on a previously established behavior-derived semantic embedding space and points to a data-driven route for incorporating human cognitive structure into MLLMs alignment.
E. Ning, Chang-De Du, Yi-Zhuo Lu et al.
· 0 citations