打破概率的枷鎖：中性邏輯作為大型語言模型中認識論不確定性的新框架

摘要

大型語言模型（LLMs）主要受概率性框架支配，其中結果概率的總和必須等於一。這種由Softmax層常施加的架構限制，導致不確定性崩塌，難以區分認知不確定性、悖論與模糊性。我們提出一項針對中性邏輯（Neutrosophic Logic）應用的實證研究——該框架將真（T）、不確定（I）與假（F）視為三個獨立維度——用以建模LLMs中的認知狀態。我們在四款OpenAI GPT模型上進行實驗，涵蓋五種語言現象：邏輯悖論、認知無知、模糊性、倫理矛盾與未來偶然性，並採用三種提示策略：中性邏輯、概率性與熵推導。研究結果顯示，中性邏輯方法允許T+I+F > 1（我們稱之為「超真值」狀態），能更豐富地呈現模型的內部狀態。在35%的評估案例中，超真值狀態自發湧現，主要出現在倫理矛盾與邏輯悖論情境下。我們證明，該方法能在模糊語境中保留真值，並為辨識與量化模型內部衝突提供穩健手段。結論指出，整合中性邏輯評估層是邁向更透明、可靠且具倫理意識的人工智慧系統的關鍵一步。

English

Large Language Models (LLMs) are predominantly governed by probabilistic frameworks in which the sum of outcome probabilities is constrained to unity. This architectural limitation, often imposed by Softmax layers, leads to a collapse of uncertainty that makes it difficult to differentiate between epistemic uncertainty, paradox, and vagueness. We present an empirical investigation of the application of Neutrosophic Logic, a framework that treats Truth (T), Indeterminacy (I), and Falsity (F) as three independent dimensions, to model epistemic states in LLMs. We conducted experiments on a family of four OpenAI GPT models across five linguistic phenomena: logical paradoxes, epistemic ignorance, vagueness, ethical contradictions, and future contingencies, under three prompting strategies: neutrosophic, probabilistic, and entropy-derived. Our findings reveal that the neutrosophic approach, by allowing T+I+F > 1, a state we term hyper-truth, provides a richer representation of a model's internal state. In 35% of evaluations, hyper-truth emerged spontaneously, predominantly under ethical contradiction and logical paradox. We demonstrate that this approach preserves truth values in fuzzy contexts and offers a robust method for identifying and quantifying internal model conflict. We conclude that the integration of neutrosophic evaluation layers is a critical step toward more transparent, reliable, and ethically aware AI systems.