AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects

• URL: http://arxiv.org/abs/2501.00559v1
• Date: Tue, 31 Dec 2024 17:45:12 GMT
• Title: AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects
• Authors: Ahmad Mustapha, Hadi Al-Khansa, Hadi Al-Mubasher, Aya Mourad, Ranam Hamoud, Hasan El-Husseini, Marwah Al-Sakkaf, Mariette Awad,
• Abstract summary: We introduce AraSTEM, a new Arabic multiple-choice question dataset aimed at evaluating Large Language Models (LLMs) knowledge in STEM subjects. This dataset spans a range of topics at different levels which requires models to demonstrate a deep understanding of scientific Arabic in order to achieve high accuracy. Our findings show that publicly available models of varying sizes struggle with this dataset, and underscores the need for more localized language models.
• Score: 0.6564819194719582
• License:
• Abstract: Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks and asses the various aspects of LLMs including knowledge and reasoning. Numerous benchmarks have been developed to evaluate LLMs knowledge, but they predominantly focus on the English language. Given that many LLMs are multilingual, relying solely on benchmarking English knowledge is insufficient. To address this issue, we introduce AraSTEM, a new Arabic multiple-choice question dataset aimed at evaluating LLMs knowledge in STEM subjects. The dataset spans a range of topics at different levels which requires models to demonstrate a deep understanding of scientific Arabic in order to achieve high accuracy. Our findings show that publicly available models of varying sizes struggle with this dataset, and underscores the need for more localized language models. The dataset is freely accessible on Hugging Face.

Related papers

• Multilingual Large Language Models: A Systematic Survey [38.972546467173565]
  This paper provides a comprehensive survey of the latest research on multilingual large language models (MLLMs) We first discuss the architecture and pre-training objectives of MLLMs, highlighting the key components and methodologies that contribute to their multilingual capabilities. We present a detailed taxonomy and roadmap covering the assessment of MLLMs' cross-lingual knowledge, reasoning, alignment with human values, safety, interpretability and specialized applications.
  arXiv  Detail & Related papers  (2024-11-17T13:21:26Z)
• How Do Multilingual Language Models Remember Facts? [50.13632788453612]
  We show that previously identified recall mechanisms in English largely apply to multilingual contexts. We localize the role of language during recall, finding that subject enrichment is language-independent. In decoder-only LLMs, FVs compose these two pieces of information in two separate stages.
  arXiv  Detail & Related papers  (2024-10-18T11:39:34Z)
• ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models [0.0]
  ArabLegalEval is a benchmark dataset for assessing the Arabic legal knowledge of Large Language Models (LLMs) Inspired by the MMLU and LegalBench datasets, ArabLegalEval consists of multiple tasks sourced from Saudi legal documents and synthesized questions. We aim to analyze the capabilities required to solve legal problems in Arabic and benchmark the performance of state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2024-08-15T07:09:51Z)
• INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages [26.13077589552484]
  Indic-QA is the largest publicly available context-grounded question-answering dataset for 11 major Indian languages from two language families. We generate a synthetic dataset using the Gemini model to create question-answer pairs given a passage, which is then manually verified for quality assurance. We evaluate various multilingual Large Language Models and their instruction-fine-tuned variants on the benchmark and observe that their performance is subpar, particularly for low-resource languages.
  arXiv  Detail & Related papers  (2024-07-18T13:57:16Z)
• Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models [7.615938028813914]
  We studied linguistic preference in a cross-language RAG-based information search setting. We found that LLMs displayed systemic bias towards information in the same language as the query language.
  arXiv  Detail & Related papers  (2024-07-07T21:26:36Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias [5.096332588720052]
  We present an overview of MLLMs, covering their evolutions, key techniques, and multilingual capacities. Thirdly, we survey the state-of-the-art studies of multilingual representations and investigate whether the current MLLMs can learn a universal language representation. Fourthly, we discuss bias on MLLMs, including its categories, evaluation metrics, and debiasing techniques.
  arXiv  Detail & Related papers  (2024-04-01T05:13:56Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages [86.90220551111096]
  Training datasets for large language models (LLMs) are often not fully disclosed. We present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages.
  arXiv  Detail & Related papers  (2023-09-17T23:49:10Z)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)
• Adapters for Enhanced Modeling of Multilingual Knowledge and Text [54.02078328453149]
  Language models have been extended to multilingual language models (MLLMs) Knowledge graphs contain facts in an explicit triple format, which require careful curation and are only available in a few high-resource languages. We propose to enhance MLLMs with knowledge from multilingual knowledge graphs (MLKGs) so as to tackle language and knowledge graph tasks across many languages.
  arXiv  Detail & Related papers  (2022-10-24T21:33:42Z)

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.