Large language models are revolutionizing several areas, including artificial creativity. However, the process of generation in machines profoundly diverges from that observed in humans. In particular, machine generation is characterized by a lack of intentionality and an underlying creative process. We propose a method called Creative Beam Search that uses Diverse Beam Search and LLM-as-a-Judge to perform response generation and response validation. The results of a qualitative experiment show how our approach can provide better output than standard sampling techniques. We also show that the response validation step is a necessary complement to the response generation step.

翻译：大型语言模型正在彻底改变包括人工智能创造力在内的多个领域。然而，机器的生成过程与人类观察到的生成过程存在深刻差异。具体而言，机器生成的特点在于缺乏意图性和底层创造性过程。我们提出了一种名为创造性束搜索的方法，该方法利用多样化束搜索和LLM-as-a-Judge来执行响应生成与响应验证。定性实验的结果表明，我们的方法相比标准采样技术能够提供更优的输出。我们还证明，响应验证步骤是响应生成步骤的必要补充。