No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Permadi, Vynska Amalia, Tan, Xingwei, Moosavi, Nafise Sadat, Aletras, Nikos
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912873512435712
author Permadi, Vynska Amalia
Tan, Xingwei
Moosavi, Nafise Sadat
Aletras, Nikos
author_facet Permadi, Vynska Amalia
Tan, Xingwei
Moosavi, Nafise Sadat
Aletras, Nikos
contents Understanding culture requires reasoning across context, tradition, and implicit social knowledge, far beyond recalling isolated facts. Yet most culturally focused question answering (QA) benchmarks rely on single-hop questions, which may allow models to exploit shallow cues rather than demonstrate genuine cultural reasoning. In this work, we introduce ID-MoCQA, the first large-scale multi-hop QA dataset for assessing the cultural understanding of large language models (LLMs), grounded in Indonesian traditions and available in both English and Indonesian. We present a new framework that systematically transforms single-hop cultural questions into multi-hop reasoning chains spanning six clue types (e.g., commonsense, temporal, geographical). Our multi-stage validation pipeline, combining expert review and LLM-as-a-judge filtering, ensures high-quality question-answer pairs. Our evaluation across state-of-the-art models reveals substantial gaps in cultural reasoning, particularly in tasks requiring nuanced inference. ID-MoCQA provides a challenging and essential benchmark for advancing the cultural competency of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03709
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
Permadi, Vynska Amalia
Tan, Xingwei
Moosavi, Nafise Sadat
Aletras, Nikos
Computation and Language
Understanding culture requires reasoning across context, tradition, and implicit social knowledge, far beyond recalling isolated facts. Yet most culturally focused question answering (QA) benchmarks rely on single-hop questions, which may allow models to exploit shallow cues rather than demonstrate genuine cultural reasoning. In this work, we introduce ID-MoCQA, the first large-scale multi-hop QA dataset for assessing the cultural understanding of large language models (LLMs), grounded in Indonesian traditions and available in both English and Indonesian. We present a new framework that systematically transforms single-hop cultural questions into multi-hop reasoning chains spanning six clue types (e.g., commonsense, temporal, geographical). Our multi-stage validation pipeline, combining expert review and LLM-as-a-judge filtering, ensures high-quality question-answer pairs. Our evaluation across state-of-the-art models reveals substantial gaps in cultural reasoning, particularly in tasks requiring nuanced inference. ID-MoCQA provides a challenging and essential benchmark for advancing the cultural competency of LLMs.
title No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
topic Computation and Language
url https://arxiv.org/abs/2602.03709