MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Deng, Yayue, Hu, Guoqiang, Sun, Haiyang, Zhang, Xiangyu, Zhang, Haoyang, Tian, Fei, Yang, Xuerui, Yu, Gang, Chng, Eng Siong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911246465368064
author Deng, Yayue
Hu, Guoqiang
Sun, Haiyang
Zhang, Xiangyu
Zhang, Haoyang
Tian, Fei
Yang, Xuerui
Yu, Gang
Chng, Eng Siong
author_facet Deng, Yayue
Hu, Guoqiang
Sun, Haiyang
Zhang, Xiangyu
Zhang, Haoyang
Tian, Fei
Yang, Xuerui
Yu, Gang
Chng, Eng Siong
contents Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first benchmark explicitly designed to evaluate SDMs in multi-turn interactive dialogue with an emphasis on emotional intelligence. Multi-Bench employs a hierarchical structure with a basic track for emotion understanding and reasoning and an advanced track for emotion support and application. It comprises five carefully designed tasks and about 3.2K samples, ranging from emotion recognition to complex reasoning and interactive dialogue, supported by a reproducible evaluation framework. We evaluate six representative SDMs on eight subsets of Multi-Bench. Results show that while current SDMs achieve good performance on basic understanding tasks, they still have room for improvement in advanced multi-turn interactive dialogue and reasoning-related tasks, particularly in emotion awareness and application.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00850
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models
Deng, Yayue
Hu, Guoqiang
Sun, Haiyang
Zhang, Xiangyu
Zhang, Haoyang
Tian, Fei
Yang, Xuerui
Yu, Gang
Chng, Eng Siong
Audio and Speech Processing
Artificial Intelligence
Computation and Language
Sound
Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first benchmark explicitly designed to evaluate SDMs in multi-turn interactive dialogue with an emphasis on emotional intelligence. Multi-Bench employs a hierarchical structure with a basic track for emotion understanding and reasoning and an advanced track for emotion support and application. It comprises five carefully designed tasks and about 3.2K samples, ranging from emotion recognition to complex reasoning and interactive dialogue, supported by a reproducible evaluation framework. We evaluate six representative SDMs on eight subsets of Multi-Bench. Results show that while current SDMs achieve good performance on basic understanding tasks, they still have room for improvement in advanced multi-turn interactive dialogue and reasoning-related tasks, particularly in emotion awareness and application.
title MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
Sound
url https://arxiv.org/abs/2511.00850