Creative beam search: LLM-as-a-judge for improving response generation
Giorgio Franceschelli
2024Computer science - artificial intelligence, computer science - computation and language, computer science - human-computer interaction, computer science - machine learning
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
Relevance Assessment
Research Gap
Notes
Notes are automatically saved as you type
Tags
Human-In-The-Loop › Autonomous GenerationCreativity Frameworks › Logical CreativityCreativity Evaluation Methods › LLM-Based EvaluationCreativity Evaluation Methods › Creativity-Specific EvaluationCreativity Evaluation Methods › Human EvaluationModel Scale › Medium (8-24)Relationship to Creativity › ExplicitResearch Focus › Architectural ResearchLevel of Analysis › Sentence-LevelLevel of Analysis › Document-Level
Search Queries
Paper ID: 81046cc4-fb14-4ecd-bd8b-ede113b93b84Added: 10/26/2025