{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"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":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"1803.05449","title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations","created":"2018-03-14","cited_by_count":294},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"1902.09666","title":"Predicting the Type and Target of Offensive Posts in Social Media","created":"2019-02-25","cited_by_count":271},{"id":"2305.15005","title":"Sentiment Analysis in the Era of Large Language Models: A Reality Check","created":"2023-05-24","cited_by_count":268},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"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":"1912.00741","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter","created":"2019-12-02","cited_by_count":210},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206},{"id":"2101.01785","title":"ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic","created":"2020-12-27","cited_by_count":166},{"id":"2305.07004","title":"Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting","created":"2023-05-11","cited_by_count":165},{"id":"2302.10198","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","created":"2023-02-19","cited_by_count":155},{"id":"2004.01670","title":"Directions in Abusive Language Training Data: Garbage In, Garbage Out","created":"2020-04-03","cited_by_count":140},{"id":"2006.07235","title":"SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)","created":"2020-06-12","cited_by_count":138},{"id":"1908.11049","title":"Multilingual and Multi-Aspect Hate Speech Analysis","created":"2019-08-29","cited_by_count":133},{"id":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123},{"id":"1708.00524","title":"Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm","created":"2017-08-01","cited_by_count":118},{"id":"2104.12250","title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","created":"2021-04-25","cited_by_count":114},{"id":"2009.05387","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","created":"2020-09-11","cited_by_count":109},{"id":"2304.04339","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","created":"2023-04-10","cited_by_count":96},{"id":"2305.15011","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","created":"2023-05-24","cited_by_count":81},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68},{"id":"2302.08956","title":"AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages","created":"2023-02-17","cited_by_count":68},{"id":"2005.00357","title":"Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research","created":"2020-05-01","cited_by_count":67},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64},{"id":"2005.05635","title":"SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis","created":"2020-05-12","cited_by_count":54},{"id":"2005.00630","title":"KLEJ: Comprehensive Benchmark for Polish Language Understanding","created":"2020-05-01","cited_by_count":51},{"id":"2009.08712","title":"The birth of Romanian BERT","created":"2020-09-18","cited_by_count":44},{"id":"1709.05404","title":"Creating and Characterizing a Diverse Corpus of Sarcasm in Dialogue","created":"2017-09-15","cited_by_count":43},{"id":"2109.05427","title":"Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification","created":"2021-09-12","cited_by_count":43},{"id":"2304.06845","title":"SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)","created":"2023-04-13","cited_by_count":41},{"id":"1803.09402","title":"Aggression-annotated Corpus of Hindi-English Code-mixed Data","created":"2018-03-26","cited_by_count":40},{"id":"2005.12503","title":"BEEP! Korean Corpus of Online News Comments for Toxic Speech Detection","created":"2020-05-26","cited_by_count":39},{"id":"2204.07660","title":"It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection","created":"2022-04-15","cited_by_count":36},{"id":"2011.01612","title":"XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection","created":"2020-11-03","cited_by_count":33},{"id":"2103.11408","title":"L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset","created":"2021-03-21","cited_by_count":31},{"id":"2012.14353","title":"DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Language","created":"2020-12-28","cited_by_count":26},{"id":"1602.07563","title":"Multilingual Twitter Sentiment Classification: The Role of Human Annotators","created":"2016-02-24","cited_by_count":24},{"id":"1803.06745","title":"Sentiment Analysis of Code-Mixed Indian Languages: An Overview of SAIL_Code-Mixed Shared Task @ICON-2017","created":"2018-03-18","cited_by_count":24},{"id":"1911.09339","title":"Emotion Recognition for Vietnamese Social Media Text","created":"2019-11-21","cited_by_count":23},{"id":"2201.08702","title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","created":"2022-01-21","cited_by_count":23},{"id":"2210.09582","title":"NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task","created":"2022-10-18","cited_by_count":23},{"id":"2011.04000","title":"Adapting a Language Model for Controlled Affective Text Generation","created":"2020-11-08","cited_by_count":22},{"id":"1712.08917","title":"Building a Sentiment Corpus of Tweets in Brazilian Portuguese","created":"2017-12-24","cited_by_count":20},{"id":"2106.09460","title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text","created":"2021-06-17","cited_by_count":18},{"id":"1710.05370","title":"NoReC: The Norwegian Review Corpus","created":"2017-10-15","cited_by_count":17},{"id":"1912.13072","title":"AraNet: A Deep Learning Toolkit for Arabic Social Media","created":"2019-12-30","cited_by_count":14},{"id":"2003.12450","title":"Semantic Enrichment of Nigerian Pidgin English for Contextual Sentiment Classification","created":"2020-03-27","cited_by_count":12},{"id":"2005.06608","title":"Understanding and Detecting Dangerous Speech in Social Media","created":"2020-05-04","cited_by_count":12},{"id":"2010.00310","title":"\"Did you really mean what you said?\" : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings","created":"2020-10-01","cited_by_count":5},{"id":"2108.00356","title":"Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning","created":"2021-08-01","cited_by_count":5},{"id":"2204.13915","title":"Czech Dataset for Cross-lingual Subjectivity Classification","created":"2022-04-29","cited_by_count":5},{"id":"2204.04611","title":"Decay No More: A Persistent Twitter Dataset for Learning Social Meaning","created":"2022-04-10","cited_by_count":3}],"next_cursor":null}