LLMs在创造性写作中表现出显著低于专业作家的不确定性
LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers
AI总结：
本文研究了LLM在创造性写作中相较于专业作家的不确定性问题，发现模型输出的不确定性显著低于人类，提出需新的对齐方法以提升创造性写作质量。
摘要：
我们主张不确定性是LLM在创造性写作中的关键且研究不足的限制因素，这种表现通常被描述为陈腐和陈词滥调。文学理论将不确定性视为创造性表达的必要条件，而当前的对齐策略会引导模型远离不确定的输出以确保事实性和减少幻觉。我们通过量化人类创作故事与模型生成延续之间的“不确定性差距”来正式化这种张力。通过在高质量叙事数据集上对28个LLM进行受控的信息论分析，我们证明人类写作在不确定性方面始终显著高于模型输出。我们发现经过指令调优和推理模型加剧了这一趋势，与基础模型相比；此外，这种差距在创造性写作领域比在功能性领域更明显，并且强烈相关于写作质量。实现人类水平的创造力需要新的不确定性意识对齐范式，这些范式能够区分破坏性幻觉与文学丰富所需的构造性不确定性。
英文摘要：
We argue that uncertainty is a key and understudied limitation of LLMs' performance in creative writing, which is often characterized as trite and cliché-ridden. Literary theory identifies uncertainty as a necessary condition for creative expression, while current alignment strategies steer models away from uncertain outputs to ensure factuality and reduce hallucination. We formalize this tension by quantifying the ``uncertainty gap'' between human-authored stories and model-generated continuations. Through a controlled information-theoretic analysis of 28 LLMs on high-quality storytelling datasets, we demonstrate that human writing consistently exhibits significantly higher uncertainty than model outputs. We find that instruction-tuned and reasoning models exacerbate this trend compared to their base counterparts; furthermore, the gap is more pronounced in creative writing than in functional domains, and shows a consistent correlation with writing quality. Achieving human-level creativity requires new uncertainty-aware alignment paradigms that can distinguish between destructive hallucinations and the constructive ambiguity required for literary richness.
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。
