English(EN) Foundations of Stochastic Lexical Calculus: Semantic Descent and Random Dynamics on Probability Simplices

新框架将LLM概率与序列状态表示联系起来

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-18 04:00

一篇新论文介绍了随机词汇演算，这是一个用于理解大型语言模型如何表示序列状态以及如何用新证据更新它们的框架。该研究定义了语义更新的条件，并证明了概率单纯形上外部随机递归的存在性和稳定性。实证测试表明，虽然原始的提示条件概率不足，但特定于提示的校准可以实现稳定的三态表示，该表示通过不变性和覆盖门。 AI

影响为理解和潜在地改进大型语言模型的状态表示能力提供了理论基础。

排序理由介绍LLM新理论框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 27 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍LLM新理论框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv stat.ML TIER_1 English(EN) · Matthew F Dixon · 2026-09-18 04:00

随机词汇微积分基础：概率单纯形上的语义下降与随机动力学

arXiv:2609.20207v1 Announce Type: cross Abstract: Large language models produce prompt-dependent probabilities over words, whereas scientific systems require uncertainty over meaningful states that can be updated as evidence arrives. We develop an observable framework for determi…

本文如何被排名

报道来源 [1]

随机词汇微积分基础：概率单纯形上的语义下降与随机动力学

相关实体

相关话题