Creative Beam Search: LLM-as-a-Judge For Improving Response Generation

TL;DR

This paper introduces Creative Beam Search, a novel method combining Diverse Beam Search with LLM-as-a-Judge to enhance response generation and validation, aiming to produce more human-like and creative outputs.

Contribution

The paper presents a new approach that integrates response validation with generation, improving the quality and creativity of machine-generated responses.

Findings

Creative Beam Search outperforms standard sampling techniques in qualitative assessments.

Response validation is essential for ensuring response quality.

The method enhances the alignment of machine responses with human-like creativity.

Abstract

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.