{"list":"other","total":114,"rows":[{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"1812.10464","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","created":"2018-12-26","cited_by_count":434},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"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":"1906.00591","title":"Evaluating Gender Bias in Machine Translation","created":"2019-06-03","cited_by_count":249},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"2407.12883","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","created":"2024-07-16","cited_by_count":158},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2004.14900","title":"MLSUM: The Multilingual Summarization Corpus","created":"2020-04-30","cited_by_count":121},{"id":"2010.11856","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","created":"2020-10-22","cited_by_count":121},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88},{"id":"2309.12053","title":"AceGPT, Localizing Large Language Models in Arabic","created":"2023-09-21","cited_by_count":75},{"id":"2210.01613","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","created":"2022-10-04","cited_by_count":72},{"id":"2504.13161","title":"Nemotron-CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training","created":"2025-04-17","cited_by_count":66},{"id":"1709.07276","title":"Speech Recognition Challenge in the Wild: Arabic MGB-3","created":"2017-09-21","cited_by_count":60},{"id":"1711.00354","title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","created":"2017-10-28","cited_by_count":58},{"id":"2002.06071","title":"FQuAD: French Question Answering Dataset","created":"2020-02-14","cited_by_count":58},{"id":"1809.00388","title":"MTNT: A Testbed for Machine Translation of Noisy Text","created":"2018-09-02","cited_by_count":54},{"id":"2004.06465","title":"Deep Learning Models for Multilingual Hate Speech Detection","created":"2020-04-14","cited_by_count":49},{"id":"1705.00823","title":"STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset","created":"2017-05-02","cited_by_count":47},{"id":"2003.08385","title":"X-Stance: A Multilingual Multi-Target Dataset for Stance Detection","created":"2020-03-18","cited_by_count":43},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40},{"id":"1912.09723","title":"SberQuAD -- Russian Reading Comprehension Dataset: Description and Analysis","created":"2019-12-20","cited_by_count":38},{"id":"1410.3791","title":"POLYGLOT-NER: Massive Multilingual Named Entity Recognition","created":"2014-10-14","cited_by_count":32},{"id":"2205.10400","title":"Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog","created":"2022-05-20","cited_by_count":30},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26},{"id":"2304.04280","title":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","created":"2023-04-09","cited_by_count":25},{"id":"2406.19232","title":"RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs","created":"2024-06-27","cited_by_count":24},{"id":"1808.07674","title":"Arap-Tweet: A Large Multi-Dialect Twitter Corpus for Gender, Age and Language Variety Identification","created":"2018-08-23","cited_by_count":23},{"id":"2202.13028","title":"Healthsheet: Development of a Transparency Artifact for Health Datasets","created":"2022-02-26","cited_by_count":23},{"id":"1911.10668","title":"JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus","created":"2019-11-25","cited_by_count":21},{"id":"2112.09323","title":"JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification","created":"2021-12-17","cited_by_count":21},{"id":"2110.06744","title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources","created":"2021-10-13","cited_by_count":20},{"id":"2002.08595","title":"KaoKore: A Pre-modern Japanese Art Facial Expression Dataset","created":"2020-02-20","cited_by_count":18},{"id":"2402.03177","title":"CIDAR: Culturally Relevant Instruction Dataset For Arabic","created":"2024-02-05","cited_by_count":17},{"id":"1710.10639","title":"JESC: Japanese-English Subtitle Corpus","created":"2017-10-29","cited_by_count":16},{"id":"2010.06436","title":"RuSemShift: a dataset of historical lexical semantic change in Russian","created":"2020-10-13","cited_by_count":16},{"id":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","cited_by_count":16},{"id":"2402.13364","title":"A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction","created":"2024-02-20","cited_by_count":16},{"id":"2407.16867","title":"From Text to Insight: Large Language Models for Materials Science Data Extraction","created":"2024-07-23","cited_by_count":15},{"id":"2005.10659","title":"RuBQ: A Russian Dataset for Question Answering over Wikidata","created":"2020-05-21","cited_by_count":14},{"id":"2007.00968","title":"Project PIAF: Building a Native French Question-Answering Dataset","created":"2020-07-02","cited_by_count":13},{"id":"2010.09381","title":"The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification","created":"2020-10-19","cited_by_count":13},{"id":"2108.13112","title":"NEREL: A Russian Dataset with Nested Named Entities, Relations and Events","created":"2021-08-30","cited_by_count":13},{"id":"2306.17674","title":"X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents","created":"2023-06-30","cited_by_count":13},{"id":"2005.06608","title":"Understanding and Detecting Dangerous Speech in Social Media","created":"2020-05-04","cited_by_count":12},{"id":"2006.11063","title":"Dataset for Automatic Summarization of Russian News","created":"2020-06-19","cited_by_count":12},{"id":"2107.13998","title":"\"Excavating AI\" Re-excavated: Debunking a Fallacious Account of the JAFFE Dataset","created":"2021-07-28","cited_by_count":12},{"id":"2303.09957","title":"A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents","created":"2023-03-17","cited_by_count":11},{"id":"2309.12676","title":"JCoLA: Japanese Corpus of Linguistic Acceptability","created":"2023-09-22","cited_by_count":11},{"id":"2103.01910","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","created":"2021-03-02","cited_by_count":10},{"id":"2104.08655","title":"DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction","created":"2021-04-17","cited_by_count":9},{"id":"2106.10161","title":"Golos: Russian Dataset for Speech Research","created":"2021-06-18","cited_by_count":9},{"id":"2010.02605","title":"DaNetQA: a yes/no Question Answering Dataset for the Russian Language","created":"2020-10-06","cited_by_count":8},{"id":"2204.05208","title":"\"FIJO\": a French Insurance Soft Skill Detection Dataset","created":"2022-04-11","cited_by_count":8},{"id":"2208.00932","title":"Masader Plus: A New Interface for Exploring +500 Arabic NLP Datasets","created":"2022-08-01","cited_by_count":8},{"id":"1610.09565","title":"Sequence-to-sequence neural network models for transliteration","created":"2016-10-29","cited_by_count":7},{"id":"1612.08989","title":"Shamela: A Large-Scale Historical Arabic Corpus","created":"2016-12-28","cited_by_count":7},{"id":"1809.03891","title":"Studying the History of the Arabic Language: Language Technology and a Large-Scale Historical Corpus","created":"2018-09-11","cited_by_count":7},{"id":"2109.13209","title":"FQuAD2.0: French Question Answering and knowing that you know nothing","created":"2021-09-27","cited_by_count":7},{"id":"2209.13750","title":"RuDSI: graph-based word sense induction dataset for Russian","created":"2022-09-28","cited_by_count":7},{"id":"2403.19259","title":"J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution","created":"2024-03-28","cited_by_count":7},{"id":"2302.07738","title":"Alloprof: a new French question-answer education dataset and its use in an information retrieval case study","created":"2023-02-10","cited_by_count":6},{"id":"2305.12720","title":"llm-japanese-dataset v0: Construction of Japanese Chat Dataset for Large Language Models and its Methodology","created":"2023-05-22","cited_by_count":6},{"id":"2309.10770","title":"FRASIMED: a Clinical French Annotated Resource Produced through Crosslingual BERT-Based Annotation Projection","created":"2023-09-19","cited_by_count":6},{"id":"1509.06928","title":"Automatic Dialect Detection in Arabic Broadcast Speech","created":"2015-09-23","cited_by_count":5},{"id":"1907.03110","title":"ANETAC: Arabic Named Entity Transliteration and Classification Dataset","created":"2019-07-06","cited_by_count":5},{"id":"2108.12626","title":"HeadlineCause: A Dataset of News Headlines for Detecting Causalities","created":"2021-08-28","cited_by_count":5},{"id":"2306.17399","title":"Japanese Lexical Complexity for Non-Native Readers: A New Dataset","created":"2023-06-30","cited_by_count":5},{"id":"2403.16099","title":"A Multi-Label Dataset of French Fake News: Human and Machine Insights","created":"2024-03-24","cited_by_count":5},{"id":"2406.17566","title":"FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts","created":"2024-06-25","cited_by_count":5},{"id":"2407.11828","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","created":"2024-07-16","cited_by_count":5},{"id":"2504.15941","title":"FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity","created":"2025-04-22","cited_by_count":5},{"id":"2202.09452","title":"From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French","created":"2022-02-18","cited_by_count":4},{"id":"2204.02718","title":"Annotation-Scheme Reconstruction for \"Fake News\" and Japanese Fake News Dataset","created":"2022-04-06","cited_by_count":4},{"id":"2306.10727","title":"Jamp: Controlled Japanese Temporal Inference Dataset for Evaluating Generalization Capacity of Language Models","created":"2023-06-19","cited_by_count":4}],"next_cursor":"100"}