引导大语言模型评估并增强创造力
Steering Large Language Models to Evaluate and Amplify Creativity
AI总结：
针对大语言模型创造力评估能力不足的问题，本研究通过提取模型生成乏味与创意内容时的内部状态差异，构建了契合人类判断的创造力衡量方法，还可用于提升生成文本的创意性。
摘要：
尽管大语言模型（LLMs）能够生成创造性文本，但它们并不擅长判断何为“创造力”。在本研究中，我们证明可以利用其自身的创意写作知识来更好地评判创意性内容。我们采用机制研究方法，提取LLM在被提示以“乏味”或“有创意”的方式作答时内部状态的差异，以此得到与人类判断高度契合的可靠创造力衡量标准。我们还表明，这些内部状态差异可在推理阶段用于提升生成文本的创意性。
英文摘要：
Although capable of generating creative text, Large Language Models (LLMs) are poor judges of what constitutes "creativity". In this work, we show that we can leverage this knowledge of how to write creatively in order to better judge what is creative. We take a mechanistic approach that extracts differences in the internal states of an LLM when prompted to respond "boringly" or "creatively" to provide a robust measure of creativity that corresponds strongly with human judgment. We also show these internal state differences can be applied to enhance the creativity of generated text at inference time.
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。
