{"list":"other","total":70,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"2405.00332","title":"A Careful Examination of Large Language Model Performance on Grade School Arithmetic","created":"2024-05-01","cited_by_count":191},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2311.14096","title":"Cultural Bias and Cultural Alignment of Large Language Models","created":"2023-11-23","cited_by_count":149},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2010.12858","title":"When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models","created":"2020-10-24","cited_by_count":131},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117},{"id":"2407.19825","title":"Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost","created":"2024-07-29","cited_by_count":109},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88},{"id":"2308.02976","title":"Spanish Pre-trained BERT Model and Evaluation Data","created":"2023-08-06","cited_by_count":81},{"id":"2102.00287","title":"Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation","created":"2021-01-30","cited_by_count":70},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68},{"id":"2011.03080","title":"EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering","created":"2020-11-05","cited_by_count":60},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57},{"id":"2306.01857","title":"Knowledge of cultural moral norms in large language models","created":"2023-06-02","cited_by_count":51},{"id":"2403.20266","title":"Latxa: An Open Language Model and Evaluation Suite for Basque","created":"2024-03-29","cited_by_count":42},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38},{"id":"2403.03640","title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","created":"2024-03-06","cited_by_count":38},{"id":"2407.12402","title":"TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish","created":"2024-07-17","cited_by_count":32},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31},{"id":"2404.06664","title":"CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge","created":"2024-04-10","cited_by_count":28},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27},{"id":"2406.07302","title":"BertaQA: How Much Do Language Models Know About Local Culture?","created":"2024-06-11","cited_by_count":23},{"id":"2404.06644","title":"Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?","created":"2024-04-09","cited_by_count":22},{"id":"2406.17789","title":"Spanish and LLM Benchmarks: is MMLU Lost in Translation?","created":"2024-05-28","cited_by_count":20},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18},{"id":"2305.12199","title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","created":"2023-05-20","cited_by_count":15},{"id":"2406.19759","title":"Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment","created":"2024-06-28","cited_by_count":14},{"id":"2402.12976","title":"The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis","created":"2024-02-20","cited_by_count":13},{"id":"2408.11841","title":"Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants","created":"2024-08-07","cited_by_count":10},{"id":"2306.07152","title":"Measuring Sentiment Bias in Machine Translation","created":"2023-06-12","cited_by_count":5},{"id":"2310.15258","title":"Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention","created":"2023-10-23","cited_by_count":4}],"next_cursor":null}