{"list":"other","total":60,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192},{"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":"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":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2007.15207","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","created":"2020-07-30","cited_by_count":153},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153},{"id":"2311.14096","title":"Cultural Bias and Cultural Alignment of Large Language Models","created":"2023-11-23","cited_by_count":149},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111},{"id":"2305.06849","title":"WebCPM: Interactive Web Search for Chinese Long-form Question Answering","created":"2023-05-11","cited_by_count":93},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91},{"id":"2309.07462","title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?","created":"2023-09-14","cited_by_count":88},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"2310.00752","title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","created":"2023-10-01","cited_by_count":70},{"id":"2403.06412","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","created":"2024-03-11","cited_by_count":66},{"id":"2402.09369","title":"Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking","created":"2024-02-14","cited_by_count":63},{"id":"2404.10199","title":"CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting","created":"2024-04-16","cited_by_count":55},{"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},{"id":"2405.04655","title":"Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense","created":"2024-05-07","cited_by_count":51},{"id":"1906.05394","title":"Neural Arabic Question Answering","created":"2019-06-12","cited_by_count":48},{"id":"2305.13632","title":"Detecting and Mitigating Hallucinations in Multilingual Summarisation","created":"2023-05-23","cited_by_count":48},{"id":"1909.07005","title":"KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension","created":"2019-09-16","cited_by_count":43},{"id":"2404.05590","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","created":"2024-04-08","cited_by_count":43},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39},{"id":"2311.01012","title":"COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances","created":"2023-11-02","cited_by_count":35},{"id":"2403.01031","title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","created":"2024-03-01","cited_by_count":32},{"id":"2009.14725","title":"A Vietnamese Dataset for Evaluating Machine Reading Comprehension","created":"2020-09-30","cited_by_count":30},{"id":"2404.06833","title":"Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge","created":"2024-04-10","cited_by_count":29},{"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},{"id":"2402.10496","title":"Comparing Hallucination Detection Metrics for Multilingual Generation","created":"2024-02-16","cited_by_count":18},{"id":"2402.18045","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","created":"2024-02-28","cited_by_count":18},{"id":"2306.05076","title":"DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models","created":"2023-06-08","cited_by_count":17},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14},{"id":"2310.08958","title":"xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark","created":"2023-10-13","cited_by_count":13},{"id":"2205.02364","title":"KenSwQuAD -- A Question Answering Dataset for Swahili Low Resource Language","created":"2022-05-04","cited_by_count":12},{"id":"2309.08210","title":"Investigating Answerability of LLMs for Long-Form Question Answering","created":"2023-09-15","cited_by_count":9},{"id":"2112.13634","title":"A Survey on non-English Question Answering Dataset","created":"2021-12-27","cited_by_count":5},{"id":"2210.10817","title":"A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition","created":"2022-10-19","cited_by_count":3}],"next_cursor":null}