arXiv:2608. 15798v1 Announce Type: new Abstract: Language models are compared by their held-out per-token cross-entropy risk---the quantity scaling laws are fitted to.
By Hanti Lin
arXiv:2606. 07623v1 Announce Type: new Abstract: This paper develops a model-theoretic framework for verifying context-conditioned language-model behavior by replacing benchmark labels with finite semantic certificates.
By Faruk Alpay, Hamdi Alakkad
The paper introduces a framework called stochastic lexical calculus that determines when probabilities produced by large language models can be used to represent sequential states in scientific systems. It defines typed measurable transformations of contextual language, constructs a minimal closed representation, and provides necessary and sufficient conditions for unique semantic updates. The authors prove bounds on irreducible nonclosure and accumulated error, and show that under average contraction an external random recursion on a probability simplex is stable and unique. Empirical tests on frozen experiments demonstrate that raw prompt-conditioned probabilities fail an invariance gate, but after prompt-specific calibration a common three-state representation satisfies stability gates and covers 28 of 30 eight-step paths, achieving 0.933 coverage at a nominal 0.90 level.
By Matthew F Dixon
arXiv:2507. 05972v3 Announce Type: replace-cross Abstract: Pseudoentropy characterizations give quantitatively precise formulations of the relationship between computational hardness and computational randomness.
By Lunjia Hu, Salil Vadhan
arXiv:2608. 14004v1 Announce Type: new Abstract: In-context learning is commonly formalized as inference from examples of a function.
By Faizanuddin Ansari, Debanjan Dutta, Swagatam Das
Knowledge graphs can guide large language models (LLMs) reasoning, but the graph seen by a system is usually a retrieved, linked, temporally scoped, and incomplete evidence state rather than a complete account of truth. We develop a theoretical perspective on grounding observable LLM trajectories under such incomplete graph evidence.