{"list":"other","total":53,"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":"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":"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"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":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"1804.06059","title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","created":"2018-04-17","cited_by_count":286},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148},{"id":"2302.12822","title":"Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data","created":"2023-02-24","cited_by_count":119},{"id":"1711.00279","title":"Paraphrase Generation with Deep Reinforcement Learning","created":"2017-11-01","cited_by_count":58},{"id":"2005.02013","title":"Neural Syntactic Preordering for Controlled Paraphrase Generation","created":"2020-05-05","cited_by_count":56},{"id":"1709.05074","title":"A Deep Generative Framework for Paraphrase Generation","created":"2017-09-15","cited_by_count":54},{"id":"2005.08417","title":"Syntax-guided Controlled Generation of Paraphrases","created":"2020-05-18","cited_by_count":47},{"id":"1906.00565","title":"Controllable Paraphrase Generation with a Syntactic Exemplar","created":"2019-06-03","cited_by_count":44},{"id":"1704.08300","title":"Diversity driven Attention Model for Query-based Abstractive Summarization","created":"2017-04-26","cited_by_count":42},{"id":"2205.14219","title":"Controllable Text Generation with Neurally-Decomposed Oracle","created":"2022-05-27","cited_by_count":41},{"id":"1906.09741","title":"Decomposable Neural Paraphrase Generation","created":"2019-06-24","cited_by_count":30},{"id":"2202.00535","title":"Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning","created":"2022-02-01","cited_by_count":25},{"id":"2105.15053","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","created":"2021-05-31","cited_by_count":22},{"id":"2305.14726","title":"In-Context Demonstration Selection with Cross Entropy Difference","created":"2023-05-24","cited_by_count":17},{"id":"2402.11138","title":"Contrastive Instruction Tuning","created":"2024-02-17","cited_by_count":17},{"id":"1801.07055","title":"Multi-Source Social Feedback of Online News Feeds","created":"2018-01-22","cited_by_count":14},{"id":"2109.00363","title":"ConRPG: Paraphrase Generation using Contexts as Regularizer","created":"2021-09-01","cited_by_count":13},{"id":"2302.04813","title":"Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting","created":"2023-02-09","cited_by_count":12},{"id":"2305.14105","title":"CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation","created":"2023-05-23","cited_by_count":12},{"id":"2310.15079","title":"Affective and Dynamic Beam Search for Story Generation","created":"2023-10-23","cited_by_count":12},{"id":"2305.13477","title":"Look-back Decoding for Open-Ended Text Generation","created":"2023-05-22","cited_by_count":10},{"id":"2011.14344","title":"Generative Pre-training for Paraphrase Generation by Representing and Predicting Spans in Exemplars","created":"2020-11-29","cited_by_count":2}],"next_cursor":null}