Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Njifenjou, Ahmed, Sucal, Virgile, Jabaian, Bassam, Lefèvre, Fabrice
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929404889792512
author Njifenjou, Ahmed
Sucal, Virgile
Jabaian, Bassam
Lefèvre, Fabrice
author_facet Njifenjou, Ahmed
Sucal, Virgile
Jabaian, Bassam
Lefèvre, Fabrice
contents Recently, various methods have been proposed to create open-domain conversational agents with Large Language Models (LLMs). These models are able to answer user queries, but in a one-way Q&A format rather than a true conversation. Fine-tuning on particular datasets is the usual way to modify their style to increase conversational ability, but this is expensive and usually only available in a few languages. In this study, we explore role-play zero-shot prompting as an efficient and cost-effective solution for open-domain conversation, using capable multilingual LLMs (Beeching et al., 2023) trained to obey instructions. We design a prompting system that, when combined with an instruction-following model - here Vicuna (Chiang et al., 2023) - produces conversational agents that match and even surpass fine-tuned models in human evaluation in French in two different tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18460
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation
Njifenjou, Ahmed
Sucal, Virgile
Jabaian, Bassam
Lefèvre, Fabrice
Computation and Language
Artificial Intelligence
Human-Computer Interaction
Recently, various methods have been proposed to create open-domain conversational agents with Large Language Models (LLMs). These models are able to answer user queries, but in a one-way Q&A format rather than a true conversation. Fine-tuning on particular datasets is the usual way to modify their style to increase conversational ability, but this is expensive and usually only available in a few languages. In this study, we explore role-play zero-shot prompting as an efficient and cost-effective solution for open-domain conversation, using capable multilingual LLMs (Beeching et al., 2023) trained to obey instructions. We design a prompting system that, when combined with an instruction-following model - here Vicuna (Chiang et al., 2023) - produces conversational agents that match and even surpass fine-tuned models in human evaluation in French in two different tasks.
title Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2406.18460