{"list":"other","total":115,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"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":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1603.01354","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","created":"2016-03-04","cited_by_count":341},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"2105.11741","title":"ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer","created":"2021-05-25","cited_by_count":231},{"id":"1806.02847","title":"A Simple Method for Commonsense Reasoning","created":"2018-06-07","cited_by_count":223},{"id":"1909.02151","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","created":"2019-09-04","cited_by_count":216},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"1511.08308","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","created":"2015-11-26","cited_by_count":201},{"id":"1609.06038","title":"Enhanced LSTM for Natural Language Inference","created":"2016-09-20","cited_by_count":200},{"id":"1910.11476","title":"A Unified MRC Framework for Named Entity Recognition","created":"2019-10-25","cited_by_count":199},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"1804.09541","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","created":"2018-04-23","cited_by_count":164},{"id":"1601.00770","title":"End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures","created":"2016-01-05","cited_by_count":161},{"id":"2304.10428","title":"GPT-NER: Named Entity Recognition via Large Language Models","created":"2023-04-20","cited_by_count":160},{"id":"1703.04826","title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","created":"2017-03-14","cited_by_count":137},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107},{"id":"2009.12677","title":"KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning","created":"2020-09-26","cited_by_count":106},{"id":"2305.08377","title":"Text Classification via Large Language Models","created":"2023-05-15","cited_by_count":106},{"id":"1905.05529","title":"Entity-Relation Extraction as Multi-Turn Question Answering","created":"2019-05-14","cited_by_count":96},{"id":"1805.02023","title":"Chinese NER Using Lattice LSTM","created":"2018-05-05","cited_by_count":81},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71},{"id":"1911.04474","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","created":"2019-11-10","cited_by_count":69},{"id":"1805.07043","title":"Aspect Based Sentiment Analysis with Gated Convolutional Networks","created":"2018-05-18","cited_by_count":65},{"id":"1809.03599","title":"Learning Named Entity Tagger using Domain-Specific Dictionary","created":"2018-09-10","cited_by_count":65},{"id":"2106.16038","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","created":"2021-06-30","cited_by_count":65},{"id":"2305.02105","title":"GPT-RE: In-context Learning for Relation Extraction using Large Language Models","created":"2023-05-03","cited_by_count":62},{"id":"2302.00618","title":"Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models","created":"2023-02-01","cited_by_count":61},{"id":"1603.04351","title":"Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations","created":"2016-03-14","cited_by_count":55},{"id":"1512.08849","title":"Learning Natural Language Inference with LSTM","created":"2015-12-30","cited_by_count":51},{"id":"1611.01604","title":"Dynamic Coattention Networks For Question Answering","created":"2016-11-05","cited_by_count":49},{"id":"1807.01396","title":"Simpler but More Accurate Semantic Dependency Parsing","created":"2018-07-03","cited_by_count":46},{"id":"1901.10457","title":"Universal Dependency Parsing from Scratch","created":"2019-01-29","cited_by_count":46},{"id":"1505.08075","title":"Transition-Based Dependency Parsing with Stack Long Short-Term Memory","created":"2015-05-29","cited_by_count":45},{"id":"1512.08422","title":"Natural Language Inference by Tree-Based Convolution and Heuristic Matching","created":"2015-12-28","cited_by_count":43},{"id":"1711.04289","title":"Neural Natural Language Inference Models Enhanced with External Knowledge","created":"2017-11-12","cited_by_count":40},{"id":"1805.01087","title":"Stack-Pointer Networks for Dependency Parsing","created":"2018-05-03","cited_by_count":36},{"id":"2105.14485","title":"CLEVE: Contrastive Pre-training for Event Extraction","created":"2021-05-30","cited_by_count":36},{"id":"2304.07987","title":"Chinese Open Instruction Generalist: A Preliminary Release","created":"2023-04-17","cited_by_count":35},{"id":"1805.04787","title":"Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling","created":"2018-05-12","cited_by_count":34},{"id":"1911.02257","title":"Hierarchical Contextualized Representation for Named Entity Recognition","created":"2019-11-06","cited_by_count":32}],"next_cursor":"100"}