Measuring Hong Kong Massive Multi-Task Language Understanding

• URL: http://arxiv.org/abs/2505.02177v1
• Date: Sun, 04 May 2025 16:39:12 GMT
• Title: Measuring Hong Kong Massive Multi-Task Language Understanding
• Authors: Chuxue Cao, Zhenghao Zhu, Junqi Zhu, Guoying Lu, Siyu Peng, Juntao Dai, Weijie Shi, Sirui Han, Yike Guo,
• Abstract summary: We introduce HKMMLU, a benchmark that evaluates Hong Kong's linguistic competence and socio-cultural knowledge.<n>The best-performing model, DeepSeek-V3, struggles to achieve an accuracy of 75%, significantly lower than that of MMLU and CMMLU.<n>This performance gap highlights the need to improve LLMs' capabilities in Hong Kong-specific language and knowledge domains.
• Score: 8.18541769113546
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multilingual understanding is crucial for the cross-cultural applicability of Large Language Models (LLMs). However, evaluation benchmarks designed for Hong Kong's unique linguistic landscape, which combines Traditional Chinese script with Cantonese as the spoken form and its cultural context, remain underdeveloped. To address this gap, we introduce HKMMLU, a multi-task language understanding benchmark that evaluates Hong Kong's linguistic competence and socio-cultural knowledge. The HKMMLU includes 26,698 multi-choice questions across 66 subjects, organized into four categories: Science, Technology, Engineering, and Mathematics (STEM), Social Sciences, Humanities, and Other. To evaluate the multilingual understanding ability of LLMs, 90,550 Mandarin-Cantonese translation tasks were additionally included. We conduct comprehensive experiments on GPT-4o, Claude 3.7 Sonnet, and 18 open-source LLMs of varying sizes on HKMMLU. The results show that the best-performing model, DeepSeek-V3, struggles to achieve an accuracy of 75\%, significantly lower than that of MMLU and CMMLU. This performance gap highlights the need to improve LLMs' capabilities in Hong Kong-specific language and knowledge domains. Furthermore, we investigate how question language, model size, prompting strategies, and question and reasoning token lengths affect model performance. We anticipate that HKMMLU will significantly advance the development of LLMs in multilingual and cross-cultural contexts, thereby enabling broader and more impactful applications.

Related papers

• Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean [8.072947878765941]
  KoGEM is designed to assess the linguistic competence of LLMs and humans in Korean.<n>It consists of 1.5k multiple-choice QA pairs covering five main categories and 16 subcategories.
  arXiv  Detail & Related papers  (2025-06-02T01:27:46Z)
• PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts [79.84059473102778]
  PolyMath is a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels.<n>Our benchmark ensures difficulty comprehensiveness, language diversity, and high-quality translation.
  arXiv  Detail & Related papers  (2025-04-25T15:39:04Z)
• HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs [0.0]
  The HKCanto-Eval benchmark is designed to evaluate large language models on Cantonese language understanding tasks.<n>It integrates cultural and linguistic nuances intrinsic to Hong Kong, providing a robust framework for assessing language models in realistic scenarios.<n>Our findings indicate that while proprietary models generally outperform open-weight models, significant limitations remain in handling Cantonese-specific linguistic and cultural knowledge.
  arXiv  Detail & Related papers  (2025-03-16T10:26:24Z)
• MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation [60.52580061637301]
  MMLU-ProX is a comprehensive benchmark covering 13 typologically diverse languages with approximately 11,829 questions per language.<n>We evaluate 25 state-of-the-art large language models (LLMs) using 5-shot chain-of-thought (CoT) and zero-shot prompting strategies, analyzing their performance across linguistic and cultural boundaries.<n>Our experiments reveal consistent performance degradation from high-resource languages to lower-resource ones, with the best models achieving over 70% accuracy on English but dropping to around 40% for languages like Swahili.
  arXiv  Detail & Related papers  (2025-03-13T15:59:20Z)
• Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages [55.36534539177367]
  This paper introduces Pangea, a multilingual multimodal large language model (MLLM) trained on a diverse 6M instruction dataset spanning 39 languages.<n>P Pangea significantly outperforms existing open-source models in multilingual settings and diverse cultural contexts.<n>We fully open-source our data, code, and trained checkpoints, to facilitate the development of inclusive and robust multilingual MLLMs.
  arXiv  Detail & Related papers  (2024-10-21T16:19:41Z)
• Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense [98.09670425244462]
  Large language models (LLMs) have demonstrated substantial commonsense understanding. This paper examines the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks.
  arXiv  Detail & Related papers  (2024-05-07T20:28:34Z)
• Measuring Taiwanese Mandarin Language Understanding [24.581360653015423]
  We present TMLU, a holistic evaluation suit tailored for assessing the advanced knowledge and reasoning capability in large language models (LLMs) TMLU consists of an array of 37 subjects across social science, STEM, humanities, Taiwan-specific content, and others, ranging from middle school to professional levels.
  arXiv  Detail & Related papers  (2024-03-29T13:56:21Z)
• Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models [79.46179534911019]
  Large language models (LLMs) have demonstrated multilingual capabilities, yet they are mostly English-centric due to imbalanced training corpora.<n>We extend the evaluation to real-world user queries and non-English-centric LLMs, offering a broader examination of multilingual performance.
  arXiv  Detail & Related papers  (2024-03-15T12:47:39Z)
• CMMLU: Measuring massive multitask language understanding in Chinese [133.70911295934746]
  This paper introduces a comprehensive Chinese benchmark that covers various subjects, including natural science, social sciences, engineering, and humanities. CMMLU fills the gap in evaluating the knowledge and reasoning capabilities of large language models within the Chinese context.
  arXiv  Detail & Related papers  (2023-06-15T15:49:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.