{"total":20,"rows":[{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530,"area":"lr"},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"id":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71,"area":"lr"},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53,"area":"lr"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16,"area":"lr"},{"id":"2305.11662","title":"Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses","created":"2023-05-19","cited_by_count":15,"area":"lr"},{"id":"2506.08768","title":"AraReasoner: Evaluating Reasoning-Based LLMs for Arabic NLP","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2310.15258","title":"Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention","created":"2023-10-23","cited_by_count":4,"area":"lr"},{"id":"2410.23511","title":"Dynamic Strategy Planning for Efficient Question Answering with Large Language Models","created":"2024-10-30","cited_by_count":3,"area":"lr"},{"id":"2508.01977","title":"TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models","created":"2025-08-04","cited_by_count":3,"area":"lr"},{"id":"2509.22472","title":"Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2305.19597","title":"What does the Failure to Reason with \"Respectively\" in Zero/Few-Shot Settings Tell Us about Language Models?","created":"2023-05-31","cited_by_count":2,"area":"lr"},{"id":"2306.16774","title":"Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages","created":"2023-06-29","cited_by_count":2,"area":"lr"},{"id":"2601.16218","title":"M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models","created":"2026-01-03","cited_by_count":2,"area":"lr"},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2508.14279","title":"GRILE: A Benchmark for Grammar Reasoning and Explanation in Romanian LLMs","created":"2025-08-19","cited_by_count":1,"area":"lr"},{"id":"2511.20399","title":"BengaliFig: A Low-Resource Challenge for Figurative and Culturally Grounded Reasoning in Bengali","created":"2025-11-25","cited_by_count":1,"area":"lr"},{"id":"2302.13201","title":"CLICKER: Attention-Based Cross-Lingual Commonsense Knowledge Transfer","created":"2023-02-26","cited_by_count":0,"area":"lr"},{"id":"2407.03004","title":"SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy","created":"2024-07-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}