{"list":"other","total":85,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"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":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"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":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"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":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"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":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1705.09655","title":"Style Transfer from Non-Parallel Text by Cross-Alignment","created":"2017-05-26","cited_by_count":248},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"1804.06437","title":"Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer","created":"2018-04-17","cited_by_count":191},{"id":"2010.05700","title":"Reformulating Unsupervised Style Transfer as Paraphrase Generation","created":"2020-10-12","cited_by_count":183},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127},{"id":"2109.03910","title":"A Recipe For Arbitrary Text Style Transfer with Large Language Models","created":"2021-09-08","cited_by_count":107},{"id":"2010.13641","title":"Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification","created":"2020-10-26","cited_by_count":98},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1905.05621","title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","created":"2019-05-14","cited_by_count":84},{"id":"2010.11982","title":"The Turking Test: Can Language Models Understand Instructions?","created":"2020-10-22","cited_by_count":82},{"id":"2004.14257","title":"Politeness Transfer: A Tag and Generate Approach","created":"2020-04-29","cited_by_count":78},{"id":"2011.08115","title":"Learning from Task Descriptions","created":"2020-11-16","cited_by_count":78},{"id":"2202.13257","title":"Controllable Natural Language Generation with Contrastive Prefixes","created":"2022-02-27","cited_by_count":75},{"id":"2002.03912","title":"A Probabilistic Formulation of Unsupervised Text Style Transfer","created":"2020-02-10","cited_by_count":70},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70},{"id":"1905.10060","title":"A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer","created":"2019-05-24","cited_by_count":65},{"id":"2112.08348","title":"Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts","created":"2021-12-15","cited_by_count":64},{"id":"1805.07513","title":"Diverse Few-Shot Text Classification with Multiple Metrics","created":"2018-05-19","cited_by_count":61},{"id":"1904.02295","title":"Evaluating Style Transfer for Text","created":"2019-04-04","cited_by_count":61},{"id":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60},{"id":"1707.01161","title":"Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models","created":"2017-07-04","cited_by_count":57},{"id":"2204.05239","title":"Exploring the Universal Vulnerability of Prompt-based Learning Paradigm","created":"2022-04-11","cited_by_count":57},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45},{"id":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35},{"id":"2203.03131","title":"Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models","created":"2022-03-07","cited_by_count":34},{"id":"2204.10019","title":"Standing on the Shoulders of Giant Frozen Language Models","created":"2022-04-21","cited_by_count":33},{"id":"2103.10685","title":"Controllable Generation from Pre-trained Language Models via Inverse Prompting","created":"2021-03-19","cited_by_count":29},{"id":"1908.06938","title":"Encoder-Agnostic Adaptation for Conditional Language Generation","created":"2019-08-19","cited_by_count":27},{"id":"2010.12771","title":"On Learning Text Style Transfer with Direct Rewards","created":"2020-10-24","cited_by_count":24},{"id":"1805.09991","title":"Lifelong Domain Word Embedding via Meta-Learning","created":"2018-05-25","cited_by_count":8}],"next_cursor":null}