{"list":"other","total":60,"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":"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"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":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"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":"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":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"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":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1912.00049","title":"Square Attack: a query-efficient black-box adversarial attack via random search","created":"2019-11-29","cited_by_count":685},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"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":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196},{"id":"1909.00505","title":"Commonsense Knowledge Mining from Pretrained Models","created":"2019-09-02","cited_by_count":189},{"id":"1807.07978","title":"Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors","created":"2018-07-20","cited_by_count":146},{"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":"1906.06919","title":"Improving Black-box Adversarial Attacks with a Transfer-based Prior","created":"2019-06-17","cited_by_count":121},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111},{"id":"2103.05327","title":"BERTese: Learning to Speak to BERT","created":"2021-03-09","cited_by_count":82},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61},{"id":"1808.09384","title":"What Makes Reading Comprehension Questions Easier?","created":"2018-08-28","cited_by_count":60},{"id":"1911.07140","title":"Black-Box Adversarial Attack with Transferable Model-based Embedding","created":"2019-11-17","cited_by_count":57},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40},{"id":"2112.03254","title":"Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention","created":"2021-12-06","cited_by_count":40},{"id":"2109.00799","title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","created":"2021-09-02","cited_by_count":39},{"id":"1911.00720","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","created":"2019-11-02","cited_by_count":35},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30},{"id":"2006.10680","title":"DisARM: An Antithetic Gradient Estimator for Binary Latent Variables","created":"2020-06-18","cited_by_count":28}],"next_cursor":null}