English(EN) Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Models

新框架通过无套利衡量语言模型理解能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员开发了一个名为 Arbitr 的新框架，旨在通过将语言模型理解问题化为无套利问题来改进其理解能力。该方法将理解定义为有界交易者无法利用模型概率输出中的逻辑不一致性来保证获利。研究发现，包括 Qwen2.5 和 Phi-3.5 在内的标准语言模型极易受到此类利用，尤其是在参数量较小的情况下，此时置信度可能具有误导性。Arbitr 训练在不损害任务准确性的情况下，显著降低了跨各种逻辑模式的可利用性。 AI

影响引入了一种评估和改进大型语言模型逻辑一致性的新颖方法，有望带来更可靠、更值得信赖的 AI 系统。

排序理由学术论文，介绍了一种新的语言模型理论框架和训练方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 21 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，介绍了一种新的语言模型理论框架和训练方法。[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 cs.AI TIER_1 English(EN) · Daniel Dragonevskiy · 2026-10-01 04:00

理解为无套利：有界荷兰式担保作为语言模型的定义和训练目标

arXiv:2609.39341v1 Announce Type: new Abstract: Does a language model merely predict tokens, or does it understand what it says? We make this question measurable by defining "understanding" through the lens of no-arbitrage. A model understands a vocabulary to a certain degree if …

本文如何被排名

报道来源 [1]

理解为无套利：有界荷兰式担保作为语言模型的定义和训练目标

相关实体

相关话题