CaLMQA: Exploring culturally specific long-form question answering across 23 languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3ABHJQ4Y9I" target="_blank" >RIV/00216208:11320/26:BHJQ4Y9I - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.acl-long.578/" target="_blank" >https://aclanthology.org/2025.acl-long.578/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.acl-long.578" target="_blank" >10.18653/v1/2025.acl-long.578</a>

Jazyk výsledku

angličtina

Název v původním jazyce

CaLMQA: Exploring culturally specific long-form question answering across 23 languages

Popis výsledku v původním jazyce

Despite rising global usage of large language models (LLMs), their ability to generate *long-form* answers to *culturally specific* questions remains unexplored in many languages. To fill this gap, we perform the first study of textual multilingual long-form QA by creating CaLMQA, a dataset of **51.7K** culturally specific questions across **23** different languages. We define culturally specific questions as those that refer to concepts unique to one or a few cultures, or have different answers depending on the cultural or regional context. We obtain these questions by crawling naturally-occurring questions from community web forums in high-resource languages, and by hiring native speakers to write questions in under-resourced, rarely-studied languages such as Fijian and Kirundi. Our data collection methodologies are translation-free, enabling the collection of culturally unique questions like “Kuber iki umwami wa mbere w'uburundi yitwa Ntare?” (Kirundi; English translation: “Why was the first king of Burundi called Ntare (Lion)?”). We evaluate factuality, relevance and surface-level quality of LLM-generated long-form answers, finding that (1) for many languages, even the best models make critical surface-level errors (e.g., answering in the wrong language, repetition), especially for low-resource languages; and (2) answers to culturally specific questions contain more factual errors than answers to culturally agnostic questions – questions that have consistent meaning and answer across many cultures. We release CaLMQA to facilitate future research in cultural and multilingual long-form QA.

Název v anglickém jazyce

CaLMQA: Exploring culturally specific long-form question answering across 23 languages

Popis výsledku anglicky

Despite rising global usage of large language models (LLMs), their ability to generate *long-form* answers to *culturally specific* questions remains unexplored in many languages. To fill this gap, we perform the first study of textual multilingual long-form QA by creating CaLMQA, a dataset of **51.7K** culturally specific questions across **23** different languages. We define culturally specific questions as those that refer to concepts unique to one or a few cultures, or have different answers depending on the cultural or regional context. We obtain these questions by crawling naturally-occurring questions from community web forums in high-resource languages, and by hiring native speakers to write questions in under-resourced, rarely-studied languages such as Fijian and Kirundi. Our data collection methodologies are translation-free, enabling the collection of culturally unique questions like “Kuber iki umwami wa mbere w'uburundi yitwa Ntare?” (Kirundi; English translation: “Why was the first king of Burundi called Ntare (Lion)?”). We evaluate factuality, relevance and surface-level quality of LLM-generated long-form answers, finding that (1) for many languages, even the best models make critical surface-level errors (e.g., answering in the wrong language, repetition), especially for low-resource languages; and (2) answers to culturally specific questions contain more factual errors than answers to culturally agnostic questions – questions that have consistent meaning and answer across many cultures. We release CaLMQA to facilitate future research in cultural and multilingual long-form QA.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

979-8-89176-251-0

ISSN

—

e-ISSN

—

Počet stran výsledku

46

Strana od-do

11772-11817

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Vienna, Austria

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—