SOURCE-LINKED INTELLIGENCE

From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

While Large Language Models have improved rapidly, many fundamental questions remain about how to evaluate the knowledge and reasoning abilities they acquire, and how such evaluations relate to the learning signals used in pre-training. In this paper, we propose ModelLog, a declarative probabilistic framework for pre-training evaluation that makes the semantic structure of model behavior explicit and provides new formal tools for relating evaluation to learning. ModelLog specifies evaluation targets as symbolic constraints over token-level predictions and measures how strongly a model's distri

Read original source ↗ Open in workspace

recordType

paper

region

Global