{"list":"other","total":62,"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":"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":"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"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":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"1905.05583","title":"How to Fine-Tune BERT for Text Classification?","created":"2019-05-14","cited_by_count":411},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"1809.05679","title":"Graph Convolutional Networks for Text Classification","created":"2018-09-15","cited_by_count":345},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"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":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"2004.12239","title":"MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification","created":"2020-04-25","cited_by_count":187},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169},{"id":"2304.10428","title":"GPT-NER: Named Entity Recognition via Large Language Models","created":"2023-04-20","cited_by_count":160},{"id":"1605.05101","title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","created":"2016-05-17","cited_by_count":144},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107},{"id":"1508.00200","title":"PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks","created":"2015-08-02","cited_by_count":96},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74},{"id":"1805.04174","title":"Joint Embedding of Words and Labels for Text Classification","created":"2018-05-10","cited_by_count":69},{"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":"2002.03067","title":"Description Based Text Classification with Reinforcement Learning","created":"2020-02-08","cited_by_count":27},{"id":"2205.13792","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","created":"2022-05-27","cited_by_count":27},{"id":"2209.04333","title":"Ranking-Enhanced Unsupervised Sentence Representation Learning","created":"2022-09-09","cited_by_count":15},{"id":"2105.07623","title":"Sentence Similarity Based on Contexts","created":"2021-05-17","cited_by_count":12},{"id":"1902.08850","title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","created":"2019-02-23","cited_by_count":10},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5}],"next_cursor":null}