@inproceedings{hu-etal-2026-vcb,
title = "{VCB} Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents",
author = "Hu, Jiliang and
Wang, Wenfu and
Li, Zuchao and
Li, Chenxing and
Zhao, Yiyang and
Li, Hanzhao and
Zhang, Liqiang and
Yu, Meng and
Yu, Dong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1659/",
pages = "33176--33200",
ISBN = "979-8-89176-395-1",
abstract = "While large audio language models (LALMs) have driven significant progress in multimodal conversational systems, current benchmarks suffer from critical limitations: they are largely English-centric, use synthetic speech, and fail to provide comprehensive, discriminative evaluation across key dimensions. To fill this gap, we present Voice Chat Bot Bench (VCB Bench), a novel, high-quality Chinese benchmark built exclusively on real human speech. VCB Bench assesses LALMs across three complementary axes: instruction following (including speech-level control beyond text commands), knowledge understanding (including general knowledge, reasoning, and daily dialogue), and robustness (evaluating stability under variations in content, environment, and speaker characteristics). Experiments conducted on representative LALMs reveal notable performance disparities and offer tangible insights for future improvements. VCB Bench serves as a reproducible and fine-grained framework, providing standardized evaluation and practical guidance for the development of Chinese voice conversational models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2026-vcb">
<titleInfo>
<title>VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiliang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenfu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuchao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxing</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanzhao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqiang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>While large audio language models (LALMs) have driven significant progress in multimodal conversational systems, current benchmarks suffer from critical limitations: they are largely English-centric, use synthetic speech, and fail to provide comprehensive, discriminative evaluation across key dimensions. To fill this gap, we present Voice Chat Bot Bench (VCB Bench), a novel, high-quality Chinese benchmark built exclusively on real human speech. VCB Bench assesses LALMs across three complementary axes: instruction following (including speech-level control beyond text commands), knowledge understanding (including general knowledge, reasoning, and daily dialogue), and robustness (evaluating stability under variations in content, environment, and speaker characteristics). Experiments conducted on representative LALMs reveal notable performance disparities and offer tangible insights for future improvements. VCB Bench serves as a reproducible and fine-grained framework, providing standardized evaluation and practical guidance for the development of Chinese voice conversational models.</abstract>
<identifier type="citekey">hu-etal-2026-vcb</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1659/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33176</start>
<end>33200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents
%A Hu, Jiliang
%A Wang, Wenfu
%A Li, Zuchao
%A Li, Chenxing
%A Zhao, Yiyang
%A Li, Hanzhao
%A Zhang, Liqiang
%A Yu, Meng
%A Yu, Dong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F hu-etal-2026-vcb
%X While large audio language models (LALMs) have driven significant progress in multimodal conversational systems, current benchmarks suffer from critical limitations: they are largely English-centric, use synthetic speech, and fail to provide comprehensive, discriminative evaluation across key dimensions. To fill this gap, we present Voice Chat Bot Bench (VCB Bench), a novel, high-quality Chinese benchmark built exclusively on real human speech. VCB Bench assesses LALMs across three complementary axes: instruction following (including speech-level control beyond text commands), knowledge understanding (including general knowledge, reasoning, and daily dialogue), and robustness (evaluating stability under variations in content, environment, and speaker characteristics). Experiments conducted on representative LALMs reveal notable performance disparities and offer tangible insights for future improvements. VCB Bench serves as a reproducible and fine-grained framework, providing standardized evaluation and practical guidance for the development of Chinese voice conversational models.
%U https://aclanthology.org/2026.findings-acl.1659/
%P 33176-33200
Markdown (Informal)
[VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents](https://aclanthology.org/2026.findings-acl.1659/) (Hu et al., Findings 2026)
ACL
- Jiliang Hu, Wenfu Wang, Zuchao Li, Chenxing Li, Yiyang Zhao, Hanzhao Li, Liqiang Zhang, Meng Yu, and Dong Yu. 2026. VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents. In Findings of the Association for Computational Linguistics: ACL 2026, pages 33176–33200, San Diego, California, United States. Association for Computational Linguistics.