校准的惊喜：一种信息论视角下的创造性质量
Calibrated Surprise: An Information-Theoretic Account of Creative Quality
AI总结：
本文提出了一种信息论框架，用于评估创造性写作的质量，通过校准的惊喜概念，结合香农互信息理论，量化了高质量文本与降质文本之间的差异。
摘要：
在大型语言模型时代，创造性写作的质量缺乏可计算的理论基础。主流方法是评分标准——将整体审美判断分解为子评分，以及通过RLHF偏好信号——用群体投票代替质量。这两种方法都绕过了文本本身的统计结构。本文提供了一种信息论基础，填补这一空白。我们提出了'校准的惊喜'作为优秀创造性写作的信息论本质。这种判断符合阅读直觉并涵盖了其对立面。这种文学判断可以精确地进行数学公式化。在完全维度约束Y下，可行的写作选择被强制进入极狭窄的空间。稀有的幸存者，从无约束的视角来看，恰好是最不可预测的选择。两者都通过香农互信息I(X;Y) = H(X) - H(X|Y)精确测量——'校准'对应H(X|Y)接近0；'惊喜'对应H(X)升高。公式的减法结构自然地将'有根据的惊喜'与'纯噪声'分开。我们使用Qwen1.5-7B的token级logprobs作为理想读者概率分布的操作代理。在20对（12中文/8英文）的高质量与系统降质文学段落中，20/20对支持核心预测：高质量段落的I(X;Y)系统性地高于其降质版本。
英文摘要：
In the era of large language models, creative writing quality lacks a computable theoretical anchor. The dominant approaches are rubric scoring -- decomposing holistic aesthetic judgment into sub-scores -- and RLHF preference signals -- replacing quality with group votes. Both bypass the statistical structure of the text itself. This paper provides an information-theoretic foundation to fill this gap. We propose 'calibrated surprise' as the information-theoretic essence of excellent creative writing. This judgment matches reading intuition and covers its opposite. This literary judgment admits a precise mathematical formulation. Under full-dimensional constraints Y, feasible writing choices are forced into an extremely narrow space. The rare survivors are, from the unconstrained perspective, exactly the least predictable choices. Both are measured precisely by Shannon mutual information I(X;Y) = H(X) - H(X|Y) -- 'calibrated' corresponds to H(X|Y) approaching 0; 'surprising' corresponds to H(X) going high. The subtraction structure of the formula naturally separates 'well-grounded surprise' from 'pure noise'. We use token-level logprobs from Qwen1.5-7B as an operational proxy for the ideal reader's probability distribution. Across 20 pairs (12 Chinese / 8 English) of high-quality vs. systematically degraded literary passages, 20/20 pairs support the core prediction: high-quality passages have systematically higher I(X;Y) than their degraded versions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
