AI RESEARCH
Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation
arXiv CS.CL
•
ArXi:2605.08522v2 Announce Type: replace The evaluation of Large Language Models (LLMs) faces a critical challenge in construct validity, where fragmented benchmarks and ad hoc metrics frequently conflate method variance, such as prompt sensitivity, with true latent capabilities. Concurrently, emerging research suggests that LLM capabilities and outputs can be modeled as continuous geometric manifolds. In this Systematization of Knowledge (SoK), we bridge these paradigms by proposing a generalized Multi-Trait Multi-Method (MTMM) framework for LLM evaluation.