English(EN) From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales

新理论解释Whisper模型中的AI幻觉

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-29 04:00

一篇新的研究论文引入了光谱敏感性定理来解释大型自动语音识别（ASR）模型中的幻觉。该定理预测了一个相变，模型从信号衰减转变为秩-1崩溃。该理论在Whisper模型上进行了测试，结果显示中间版本经历了结构分解，而较大的模型则进入了一个寻求压缩的吸引子状态，使其与声学证据脱钩。 AI

影响提供了一个理论框架来理解并可能减轻ASR模型中的幻觉。

排序理由学术论文，详细介绍了新的理论框架和实验验证。[lever_c_demoted from research: ic=1 ai=1.0]

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了新的理论框架和实验验证。[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, safety; 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: 103 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Ivan Viakhirev, Kirill Borodin, Grach Mkrtchian · 2026-06-29 04:00

从离散到吸引：Whisper模型尺度下幻觉的光谱动力学

arXiv:2604.08591v2 Announce Type: replace-cross Abstract: Hallucinations in large ASR models present a critical safety risk. In this work, we propose the \textit{Spectral Sensitivity Theorem}, which predicts a phase transition in deep networks from a dispersive regime (signal dec…