{"total":88,"rows":[{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2411.16508","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","created":"2024-11-25","cited_by_count":55,"area":"wm"},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"area":null},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39,"area":"lr"},{"id":"2502.10361","title":"Enhancing Multilingual LLM Pretraining with Model-Based Data Selection","created":"2025-02-14","cited_by_count":35,"area":null},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2406.07302","title":"BertaQA: How Much Do Language Models Know About Local Culture?","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22,"area":null},{"id":"2410.18976","title":"CAMEL-Bench: A Comprehensive Arabic LMM Benchmark","created":"2024-10-24","cited_by_count":17,"area":"lr"},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2411.05049","title":"ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding","created":"2024-11-07","cited_by_count":15,"area":null},{"id":"2506.19468","title":"MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2409.17912","title":"Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect","created":"2024-09-26","cited_by_count":13,"area":null},{"id":"2412.17933","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2408.07983","title":"ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2409.12623","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","created":"2024-09-19","cited_by_count":10,"area":null},{"id":"2506.15629","title":"Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability","created":"2025-06-18","cited_by_count":10,"area":"lr"},{"id":"2508.08287","title":"Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2502.11020","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2510.13430","title":"Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps","created":"2025-10-15","cited_by_count":9,"area":null},{"id":"2408.13534","title":"Cultural Adaptation of Menus: A Fine-Grained Approach","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2502.00094","title":"AIN: The Arabic INclusive Large Multimodal Model","created":"2025-01-31","cited_by_count":8,"area":"mllm"},{"id":"2502.13520","title":"A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2412.03253","title":"Alignment at Pre-training! Towards Native Alignment for Arabic LLMs","created":"2024-12-04","cited_by_count":7,"area":"alignment"},{"id":"2503.21910","title":"JEEM: Vision-Language Understanding in Four Arabic Dialects","created":"2025-03-27","cited_by_count":7,"area":"mllm"},{"id":"2505.18951","title":"BnMMLU: Measuring Massive Multitask Language Understanding in Bengali","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2507.04569","title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts","created":"2025-07-06","cited_by_count":7,"area":null},{"id":"2603.23750","title":"IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge","created":"2026-03-24","cited_by_count":7,"area":null},{"id":"2502.12829","title":"KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2503.15003","title":"LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2506.01920","title":"From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2509.03162","title":"SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala","created":"2025-09-03","cited_by_count":6,"area":"lr"},{"id":"2510.27543","title":"DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models","created":"2025-10-31","cited_by_count":6,"area":null},{"id":"2503.17739","title":"Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection","created":"2025-03-22","cited_by_count":5,"area":"synth"},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.00288","title":"Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2507.22603","title":"BALSAM: A Platform for Benchmarking Arabic Large Language Models","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2409.08564","title":"Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2412.12310","title":"Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2505.13498","title":"IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation","created":"2025-05-16","cited_by_count":4,"area":"lr"},{"id":"2410.08674","title":"Guidelines for Fine-grained Sentence-level Arabic Readability Annotation","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2505.16591","title":"Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2505.24409","title":"When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering","created":"2025-05-30","cited_by_count":3,"area":"lr"},{"id":"2608.25089","title":"Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2408.15793","title":"Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2501.05478","title":"Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2510.14014","title":"CRaFT: An Explanation-Based Framework for Evaluating Cultural Reasoning in Multilingual Language Models","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2510.21193","title":"Estonian Native Large Language Model Benchmark","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.14295","title":"AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2507.19699","title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2508.14913","title":"Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2510.24438","title":"Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content","created":"2025-10-28","cited_by_count":1,"area":"agents"},{"id":"2602.17054","title":"ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2606.01995","title":"CARTE: A Benchmark for Mapping Language Model Knowledge Across France","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.08025","title":"Arabic Sentence Segmentation Across Genres and Punctuation Conditions","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2411.12921","title":"A Comparative Study of Text Retrieval Models on DaReCzech","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2412.10105","title":"MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2510.13481","title":"Tahakom LLM Guidelines and Recipes: From Pre-training Data to an Arabic LLM","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.18411","title":"SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.21580","title":"Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.01161","title":"The Role of Dataset Linguistic Structure in the Cultural Awareness of Large Language Models","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.18776","title":"ArabicNumBench: Evaluating Arabic Number Reading in Large Language Models","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.06421","title":"State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.06456","title":"Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.15613","title":"Toward LLMs Beyond English-Centric Development","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.28827","title":"RightNow-Arabic-0.5B-Turbo: An Open Sub-1B Arabic Language Model via Vocabulary Injection and Edge-First Deployment","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2606.07167","title":"UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.07422","title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.16562","title":"MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.21460","title":"Evaluation of Small Language Models for Arabic Language Processing","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.11127","title":"Do LLMs Fabricate Legal Citations? A Bilingual Benchmark on Saudi Data Protection Law and the GDPR","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.00207","title":"Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.18336","title":"Measuring the Partial-Credit Gap: A Strict Benchmark on Vietnam's 2025 Convex Marking Scheme","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18361","title":"Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.10153","title":"YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.13980","title":"Mizan: A National Benchmark for Evaluating Large Language Models on Iraqi Arabic and the Iraqi Civic Context","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.16006","title":"Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.22038","title":"QuranicMMLU: A Cognitively-Aware Benchmark for Evaluating Generative AI Solutions on Quranic Linguistic Knowledge","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.23955","title":"Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.05458","title":"Measuring and Reducing Cross-Vendor Mismatch in Language Models","created":"2026-10-04","cited_by_count":0,"area":"moe"}],"next_cursor":null}