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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Franceschelli, Giorgio, Musolesi, Mirco
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909338002522112
author Franceschelli, Giorgio
Musolesi, Mirco
author_facet Franceschelli, Giorgio
Musolesi, Mirco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00099
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Creative Beam Search: LLM-as-a-Judge For Improving Response Generation
Franceschelli, Giorgio
Musolesi, Mirco
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Machine Learning
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.
title Creative Beam Search: LLM-as-a-Judge For Improving Response Generation
topic Artificial Intelligence
Computation and Language
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2405.00099