用三值逻辑让大模型识别自身不确定性，更懂自己哪里不懂。
Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models
- 引入独立的真、不确定、假三维度，突破概率和为1的限制
- 35%情况下自发出现超真态，尤其在伦理矛盾与悖论中表现突出
- 适合追求可解释性、伦理安全的AI系统开发者
大型语言模型（LLM）通常基于概率框架运行，其输出概率总和被约束为1，这种架构限制导致难以区分认知不确定性、悖论与模糊性。本文实证研究将中立逻辑（Neutrosophic Logic）应用于LLM，该框架将真（T）、不确定（I）、假（F）视为独立维度。我们在四款OpenAI GPT模型上，针对逻辑悖论、认知无知、模糊性、伦理矛盾和未来可能性五类语言现象，在三种提示策略（中立、概率、熵导）下进行实验。结果表明，允许T+I+F > 1（称为超真态）的中立方法，能更丰富地表征模型内部状态。在35%的评估中，超真态自发出现，主要出现在伦理矛盾与逻辑悖论场景。该方法在模糊情境中保持真值稳定，提供识别与量化模型内冲突的有效途径。结论指出，集成中立评估层是实现更透明、可靠、具伦理意识AI系统的关键一步。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。