{"list":"other","total":86,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"id":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2302.10205","title":"ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT","created":"2023-02-20","cited_by_count":250},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2203.12277","title":"Unified Structure Generation for Universal Information Extraction","created":"2022-03-23","cited_by_count":221},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2104.07650","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","created":"2021-04-15","cited_by_count":180},{"id":"1807.02478","title":"CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction","created":"2018-07-04","cited_by_count":170},{"id":"2304.08085","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","created":"2023-04-17","cited_by_count":170},{"id":"2105.07464","title":"Few-NERD: A Few-Shot Named Entity Recognition Dataset","created":"2021-05-16","cited_by_count":152},{"id":"1605.05101","title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","created":"2016-05-17","cited_by_count":144},{"id":"2303.13547","title":"A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability","created":"2023-03-12","cited_by_count":119},{"id":"1711.05073","title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","created":"2017-11-14","cited_by_count":110},{"id":"2004.13590","title":"MAVEN: A Massive General Domain Event Detection Dataset","created":"2020-04-28","cited_by_count":104},{"id":"2012.04373","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","created":"2020-12-08","cited_by_count":104},{"id":"2305.05003","title":"Revisiting Relation Extraction in the era of Large Language Models","created":"2023-05-08","cited_by_count":102},{"id":"2304.10145","title":"Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks","created":"2023-04-20","cited_by_count":89},{"id":"1807.04905","title":"Ultra-Fine Entity Typing","created":"2018-07-13","cited_by_count":87},{"id":"1805.02023","title":"Chinese NER Using Lattice LSTM","created":"2018-05-05","cited_by_count":81},{"id":"1904.09679","title":"Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension","created":"2019-04-21","cited_by_count":81},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75},{"id":"2002.11893","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","created":"2020-02-27","cited_by_count":66},{"id":"2004.04100","title":"KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation","created":"2020-04-08","cited_by_count":59},{"id":"2307.09007","title":"On the (In)Effectiveness of Large Language Models for Chinese Text Correction","created":"2023-07-18","cited_by_count":54},{"id":"2308.06966","title":"EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce","created":"2023-08-14","cited_by_count":49},{"id":"2301.03282","title":"Universal Information Extraction as Unified Semantic Matching","created":"2023-01-09","cited_by_count":48},{"id":"2104.04697","title":"ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning","created":"2021-04-10","cited_by_count":46},{"id":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45},{"id":"2010.08738","title":"RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling","created":"2020-10-17","cited_by_count":41},{"id":"2209.12616","title":"T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition","created":"2022-09-09","cited_by_count":37},{"id":"2003.01355","title":"CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model","created":"2020-03-03","cited_by_count":36},{"id":"2203.08556","title":"LEVEN: A Large-Scale Chinese Legal Event Detection Dataset","created":"2022-03-16","cited_by_count":36},{"id":"1607.06275","title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","created":"2016-07-21","cited_by_count":35},{"id":"2305.15444","title":"PromptNER: Prompting For Named Entity Recognition","created":"2023-05-24","cited_by_count":35},{"id":"2204.06347","title":"WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types","created":"2022-04-13","cited_by_count":34},{"id":"2212.00196","title":"Data-Efficient Finetuning Using Cross-Task Nearest Neighbors","created":"2022-12-01","cited_by_count":26},{"id":"2004.14283","title":"SubjQA: A Dataset for Subjectivity and Review Comprehension","created":"2020-04-29","cited_by_count":24},{"id":"2306.05539","title":"Instruction Tuned Models are Quick Learners","created":"2023-05-17","cited_by_count":21},{"id":"2001.04351","title":"CLUENER2020: Fine-grained Named Entity Recognition Dataset and Benchmark for Chinese","created":"2020-01-13","cited_by_count":19},{"id":"2208.14536","title":"MultiCoNER: A Large-scale Multilingual dataset for Complex Named Entity Recognition","created":"2022-08-30","cited_by_count":19},{"id":"1910.05040","title":"BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels","created":"2019-10-11","cited_by_count":17},{"id":"2305.06586","title":"SemEval-2023 Task 2: Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2)","created":"2023-05-11","cited_by_count":17},{"id":"2006.12146","title":"ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion","created":"2020-06-22","cited_by_count":16},{"id":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","cited_by_count":13},{"id":"2211.04215","title":"Active Relation Discovery: Towards General and Label-aware Open Relation Extraction","created":"2022-11-08","cited_by_count":10},{"id":"2305.14898","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","created":"2023-05-24","cited_by_count":10},{"id":"1907.12801","title":"IPRE: a Dataset for Inter-Personal Relationship Extraction","created":"2019-07-30","cited_by_count":8},{"id":"2004.08825","title":"A Chinese Corpus for Fine-grained Entity Typing","created":"2020-04-19","cited_by_count":7},{"id":"2006.10207","title":"Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections","created":"2020-06-17","cited_by_count":4},{"id":"2304.12272","title":"AMR Parsing with Instruction Fine-tuned Pre-trained Language Models","created":"2023-04-24","cited_by_count":3},{"id":"2206.12094","title":"Unified BERT for Few-shot Natural Language Understanding","created":"2022-06-24","cited_by_count":2}],"next_cursor":null}