IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Bo, Wang, Zhiheng, Gong, Heyang, Lu, Chaochao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912411000242176
author Peng, Bo
Wang, Zhiheng
Gong, Heyang
Lu, Chaochao
author_facet Peng, Bo
Wang, Zhiheng
Gong, Heyang
Lu, Chaochao
contents In modern dialogue systems, the ability to implicitly infer user backgrounds from conversations and leverage this information for personalized assistance is crucial. However, the scarcity of high-quality data remains a fundamental challenge to evaluating and improving this capability. Traditional dataset construction methods are labor-intensive, resource-demanding, and raise privacy concerns. To address these issues, we propose a novel approach for automatic synthetic data generation and introduce the Implicit Personalized Dialogue (IP-Dialog) benchmark along with a training dataset, covering 10 tasks and 12 user attribute types. Additionally, we develop a systematic evaluation framework with four metrics to assess both attribute awareness and reasoning capabilities. We further propose five causal graphs to elucidate models' reasoning pathways during implicit personalization. Extensive experiments yield insightful observations and prove the reliability of our dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02449
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data
Peng, Bo
Wang, Zhiheng
Gong, Heyang
Lu, Chaochao
Computation and Language
Human-Computer Interaction
In modern dialogue systems, the ability to implicitly infer user backgrounds from conversations and leverage this information for personalized assistance is crucial. However, the scarcity of high-quality data remains a fundamental challenge to evaluating and improving this capability. Traditional dataset construction methods are labor-intensive, resource-demanding, and raise privacy concerns. To address these issues, we propose a novel approach for automatic synthetic data generation and introduce the Implicit Personalized Dialogue (IP-Dialog) benchmark along with a training dataset, covering 10 tasks and 12 user attribute types. Additionally, we develop a systematic evaluation framework with four metrics to assess both attribute awareness and reasoning capabilities. We further propose five causal graphs to elucidate models' reasoning pathways during implicit personalization. Extensive experiments yield insightful observations and prove the reliability of our dataset.
title IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2506.02449