@inproceedings{al-kautsar-etal-2026-culturetalk,
title = "{CULTURETALK}-{ID}: A Multi-Task Dialogue Benchmark for Cultural Commonsense in {I}ndonesian Local Languages",
author = "Al Kautsar, Muhammad Dehan and
Pranida, Salsabila Zahirah and
Elbouardi, Bilal and
Koto, Fajri",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.147/",
pages = "2888--2912",
ISBN = "979-8-89176-444-6",
abstract = "Culture shapes how people interpret and navigate social interactions, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. We introduce CULTURETALK-ID, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity. CULTURETALK-ID introduces three complementary tasks, namely dialogue-based multiple choice cultural commonsense reasoning, culturally faithful machine translation, and language steering, which jointly probe whether LLMs can understand, transfer, and generate culturally grounded language. Our results show that open-source models still underperform, particularly in the generation task and local language settings, highlighting a gap in their ability to capture and generate culturally grounded knowledge in conversational contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-kautsar-etal-2026-culturetalk">
<titleInfo>
<title>CULTURETALK-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Dehan</namePart>
<namePart type="family">Al Kautsar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salsabila</namePart>
<namePart type="given">Zahirah</namePart>
<namePart type="family">Pranida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bilal</namePart>
<namePart type="family">Elbouardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</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>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</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">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Culture shapes how people interpret and navigate social interactions, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. We introduce CULTURETALK-ID, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity. CULTURETALK-ID introduces three complementary tasks, namely dialogue-based multiple choice cultural commonsense reasoning, culturally faithful machine translation, and language steering, which jointly probe whether LLMs can understand, transfer, and generate culturally grounded language. Our results show that open-source models still underperform, particularly in the generation task and local language settings, highlighting a gap in their ability to capture and generate culturally grounded knowledge in conversational contexts.</abstract>
<identifier type="citekey">al-kautsar-etal-2026-culturetalk</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.147/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2888</start>
<end>2912</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CULTURETALK-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages
%A Al Kautsar, Muhammad Dehan
%A Pranida, Salsabila Zahirah
%A Elbouardi, Bilal
%A Koto, Fajri
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F al-kautsar-etal-2026-culturetalk
%X Culture shapes how people interpret and navigate social interactions, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. We introduce CULTURETALK-ID, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity. CULTURETALK-ID introduces three complementary tasks, namely dialogue-based multiple choice cultural commonsense reasoning, culturally faithful machine translation, and language steering, which jointly probe whether LLMs can understand, transfer, and generate culturally grounded language. Our results show that open-source models still underperform, particularly in the generation task and local language settings, highlighting a gap in their ability to capture and generate culturally grounded knowledge in conversational contexts.
%U https://aclanthology.org/2026.findings-aacl.147/
%P 2888-2912
Markdown (Informal)
[CULTURETALK-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages](https://aclanthology.org/2026.findings-aacl.147/) (Al Kautsar et al., Findings 2026)
ACL