Neutrosophic Sets and Systems
Abstract
For twenty-five years, neutrosophic logic has assigned independent degrees of truth (T), indeterminacy (I), and falsity (F) to model epistemic states that classical and fuzzy semantics cannot express. All previous applications, however, measured these components on outputs: answers, judgments, expert evaluations. This paper reports, to our knowledge, the first neutrosophic reading of components inside the internal representations of a large language model. Using the recently released Jacobian lens on Qwen3.5-4B, we project intermediate-layer readouts onto lexicons of support, refutation, and hedging, obtaining layer-wise (T, I, F) profiles under three epistemic conditions (conflicting evidence, first-person false belief, factual control; n = 20 each). What survives the controls is that the neutrosophic verdict balance B = log10(F) - log10(T) tracks the polarity of the evidence under identical templates and residually discriminates false from true first-person beliefs. We argue that the independence of the neutrosophic components is precisely what makes this measurement and its self-correction possible, and we distill the two-battery design into a reusable protocol for neutrosophic auditing of language model internals.
Recommended Citation
Leyva, Maikel; Alexis Matheu Perez; and Florentin Smarandache. "Internal Verdicts Track Evidence: A Template-Controlled Neutrosophic Reading of Epistemic States in Large Language Models via the Jacobian Lens." Neutrosophic Sets and Systems 101, 1 (2026). https://digitalrepository.unm.edu/nss_journal/vol101/iss1/2