{"list":"other","total":53,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","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":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2502.02737","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","created":"2025-02-04","cited_by_count":335},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278},{"id":"1908.11828","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","created":"2019-08-30","cited_by_count":264},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"1906.02569","title":"Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild","created":"2019-06-06","cited_by_count":178},{"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":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129},{"id":"2409.16235","title":"EuroLLM: Multilingual Language Models for Europe","created":"2024-09-24","cited_by_count":106},{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69},{"id":"2104.08726","title":"AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages","created":"2021-04-18","cited_by_count":50},{"id":"2108.06130","title":"Semantic Answer Similarity for Evaluating Question Answering Models","created":"2021-08-13","cited_by_count":47},{"id":"1911.08354","title":"Energy Usage Reports: Environmental awareness as part of algorithmic accountability","created":"2019-11-19","cited_by_count":44},{"id":"2404.05590","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","created":"2024-04-08","cited_by_count":43},{"id":"2403.20266","title":"Latxa: An Open Language Model and Evaluation Suite for Basque","created":"2024-03-29","cited_by_count":42},{"id":"2207.06814","title":"BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling","created":"2022-07-14","cited_by_count":30},{"id":"1806.04291","title":"Challenges of language technologies for the indigenous languages of the Americas","created":"2018-06-12","cited_by_count":29},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27},{"id":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26},{"id":"2401.07955","title":"A Study on Large Language Models' Limitations in Multiple-Choice Question Answering","created":"2024-01-15","cited_by_count":22},{"id":"2410.03730","title":"Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs","created":"2024-09-30","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":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16},{"id":"2101.11978","title":"Semi-automatic Generation of Multilingual Datasets for Stance Detection in Twitter","created":"2021-01-28","cited_by_count":10},{"id":"2403.09159","title":"Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation","created":"2024-03-14","cited_by_count":7},{"id":"2501.02266","title":"LLMzSz{\\L}: a comprehensive LLM benchmark for Polish","created":"2025-01-04","cited_by_count":7},{"id":"2406.15227","title":"A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation","created":"2024-06-21","cited_by_count":6},{"id":"2410.12445","title":"Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMs","created":"2024-10-16","cited_by_count":6},{"id":"2404.07053","title":"Meta4XNLI: A Crosslingual Parallel Corpus for Metaphor Detection and Interpretation","created":"2024-04-10","cited_by_count":5},{"id":"2406.17535","title":"Disce aut Deficere: Evaluating LLMs Proficiency on the INVALSI Italian Benchmark","created":"2024-06-25","cited_by_count":5},{"id":"2502.09387","title":"Truth Knows No Language: Evaluating Truthfulness Beyond English","created":"2025-02-13","cited_by_count":5},{"id":"2406.13893","title":"Open Generative Large Language Models for Galician","created":"2024-06-19","cited_by_count":3},{"id":"2404.07611","title":"NoticIA: A Clickbait Article Summarization Dataset in Spanish","created":"2024-04-11","cited_by_count":2},{"id":"2407.17479","title":"The #Somos600M Project: Generating NLP resources that represent the diversity of the languages from LATAM, the Caribbean, and Spain","created":"2024-07-01","cited_by_count":2},{"id":"2502.16721","title":"Speed and Conversational Large Language Models: Not All Is About Tokens per Second","created":"2025-02-23","cited_by_count":2}],"next_cursor":null}