@inproceedings{joe-etal-2026-kommerce,
title = "{K}o{MMERCE}: A {K}orean Multimodal and Multitask Evaluation Benchmark for Reliable Conversational {E}-commerce Agents",
author = "Joe, Byunggill and
Kim, San and
Jung, Minyoung and
Shin, Dong Hyok and
Sung, Yu-Jeong and
Shin, Saim",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.185/",
pages = "4118--4150",
ISBN = "979-8-89176-439-2",
abstract = "E-commerce conversations are increasingly multimodal, yet end-to-end response scores cannot localize which dialogue competence failed, and no public benchmark evaluates finegrained multimodal dialogue understanding for Korean commercial agents. We present KoMMERCE, a Korean multimodal fashion-domain benchmark that coordinates nine fine-grained dialogue understanding tasks on the same conversations: sentiment, intent, and strategy classification;image and text knowledge retrieval;dialogue state tracking; span detection; coreference resolution; and the first formulation of cross-modal dialogue relation extraction. The corpus contains 15,293 dyadic role-play dialogues under two-stage quality control. Baselines on six frontier multimodal LLMs reveal task-conditional patterns that should inform deployment choices: no model wins all nine tasks, and context length affects accuracy differently from one task to another."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joe-etal-2026-kommerce">
<titleInfo>
<title>KoMMERCE: A Korean Multimodal and Multitask Evaluation Benchmark for Reliable Conversational E-commerce Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Byunggill</namePart>
<namePart type="family">Joe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">San</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minyoung</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="given">Hyok</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Jeong</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saim</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>E-commerce conversations are increasingly multimodal, yet end-to-end response scores cannot localize which dialogue competence failed, and no public benchmark evaluates finegrained multimodal dialogue understanding for Korean commercial agents. We present KoMMERCE, a Korean multimodal fashion-domain benchmark that coordinates nine fine-grained dialogue understanding tasks on the same conversations: sentiment, intent, and strategy classification;image and text knowledge retrieval;dialogue state tracking; span detection; coreference resolution; and the first formulation of cross-modal dialogue relation extraction. The corpus contains 15,293 dyadic role-play dialogues under two-stage quality control. Baselines on six frontier multimodal LLMs reveal task-conditional patterns that should inform deployment choices: no model wins all nine tasks, and context length affects accuracy differently from one task to another.</abstract>
<identifier type="citekey">joe-etal-2026-kommerce</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.185/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4118</start>
<end>4150</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KoMMERCE: A Korean Multimodal and Multitask Evaluation Benchmark for Reliable Conversational E-commerce Agents
%A Joe, Byunggill
%A Kim, San
%A Jung, Minyoung
%A Shin, Dong Hyok
%A Sung, Yu-Jeong
%A Shin, Saim
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F joe-etal-2026-kommerce
%X E-commerce conversations are increasingly multimodal, yet end-to-end response scores cannot localize which dialogue competence failed, and no public benchmark evaluates finegrained multimodal dialogue understanding for Korean commercial agents. We present KoMMERCE, a Korean multimodal fashion-domain benchmark that coordinates nine fine-grained dialogue understanding tasks on the same conversations: sentiment, intent, and strategy classification;image and text knowledge retrieval;dialogue state tracking; span detection; coreference resolution; and the first formulation of cross-modal dialogue relation extraction. The corpus contains 15,293 dyadic role-play dialogues under two-stage quality control. Baselines on six frontier multimodal LLMs reveal task-conditional patterns that should inform deployment choices: no model wins all nine tasks, and context length affects accuracy differently from one task to another.
%U https://aclanthology.org/2026.aacl-long.185/
%P 4118-4150
Markdown (Informal)
[KoMMERCE: A Korean Multimodal and Multitask Evaluation Benchmark for Reliable Conversational E-commerce Agents](https://aclanthology.org/2026.aacl-long.185/) (Joe et al., AACL-IJCNLP 2026)
ACL