Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Joko, Hideaki, Chatterjee, Shubham, Ramsay, Andrew, de Vries, Arjen P., Dalton, Jeff, Hasibi, Faegheh
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916236853510144
author Joko, Hideaki
Chatterjee, Shubham
Ramsay, Andrew
de Vries, Arjen P.
Dalton, Jeff
Hasibi, Faegheh
author_facet Joko, Hideaki
Chatterjee, Shubham
Ramsay, Andrew
de Vries, Arjen P.
Dalton, Jeff
Hasibi, Faegheh
contents The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dialogue datasets that span multiple sessions and reflect real-world user preferences. Previous approaches rely on experts in a wizard-of-oz setup that is difficult to scale, particularly for personalized tasks. Our method, LAPS, addresses this by using large language models (LLMs) to guide a single human worker in generating personalized dialogues. This method has proven to speed up the creation process and improve quality. LAPS can collect large-scale, human-written, multi-session, and multi-domain conversations, including extracting user preferences. When compared to existing datasets, LAPS-produced conversations are as natural and diverse as expert-created ones, which stays in contrast with fully synthetic methods. The collected dataset is suited to train preference extraction and personalized response generation. Our results show that responses generated explicitly using extracted preferences better match user's actual preferences, highlighting the value of using extracted preferences over simple dialogue history. Overall, LAPS introduces a new method to leverage LLMs to create realistic personalized conversational data more efficiently and effectively than previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03480
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search
Joko, Hideaki
Chatterjee, Shubham
Ramsay, Andrew
de Vries, Arjen P.
Dalton, Jeff
Hasibi, Faegheh
Information Retrieval
The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dialogue datasets that span multiple sessions and reflect real-world user preferences. Previous approaches rely on experts in a wizard-of-oz setup that is difficult to scale, particularly for personalized tasks. Our method, LAPS, addresses this by using large language models (LLMs) to guide a single human worker in generating personalized dialogues. This method has proven to speed up the creation process and improve quality. LAPS can collect large-scale, human-written, multi-session, and multi-domain conversations, including extracting user preferences. When compared to existing datasets, LAPS-produced conversations are as natural and diverse as expert-created ones, which stays in contrast with fully synthetic methods. The collected dataset is suited to train preference extraction and personalized response generation. Our results show that responses generated explicitly using extracted preferences better match user's actual preferences, highlighting the value of using extracted preferences over simple dialogue history. Overall, LAPS introduces a new method to leverage LLMs to create realistic personalized conversational data more efficiently and effectively than previous methods.
title Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search
topic Information Retrieval
url https://arxiv.org/abs/2405.03480