Creative Beam Search: LLM-as-a-Judge For Improving Response Generation
This addresses the problem of improving creative response generation in large language models for AI applications, but it appears incremental as it builds on existing techniques.
The paper tackles the lack of intentionality and creative process in machine generation by proposing Creative Beam Search, which uses Diverse Beam Search and LLM-as-a-Judge for response generation and validation, showing it provides better output than standard sampling techniques in qualitative experiments.
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.