{"list":"other","total":64,"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":"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":"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"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":"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":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"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":"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":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"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":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"1904.11694","title":"Neural Logic Machines","created":"2019-04-26","cited_by_count":145},{"id":"2004.04487","title":"Injecting Numerical Reasoning Skills into Language Models","created":"2020-04-09","cited_by_count":133},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109},{"id":"2109.03910","title":"A Recipe For Arbitrary Text Style Transfer with Large Language Models","created":"2021-09-08","cited_by_count":107},{"id":"1410.4615","title":"Learning to Execute","created":"2014-10-17","cited_by_count":106},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"2109.03034","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","created":"2021-09-07","cited_by_count":82},{"id":"1711.00482","title":"Learning with Latent Language","created":"2017-11-01","cited_by_count":75},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"1910.06701","title":"NumNet: Machine Reading Comprehension with Numerical Reasoning","created":"2019-10-15","cited_by_count":59},{"id":"1805.03818","title":"Training Classifiers with Natural Language Explanations","created":"2018-05-10","cited_by_count":58},{"id":"1909.00109","title":"Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehension","created":"2019-08-31","cited_by_count":51},{"id":"1811.00720","title":"Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems","created":"2018-11-02","cited_by_count":49},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44},{"id":"1908.05514","title":"A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning","created":"2019-08-15","cited_by_count":41},{"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":"2006.08084","title":"Neural Execution Engines: Learning to Execute Subroutines","created":"2020-06-15","cited_by_count":36},{"id":"1704.06611","title":"Making Neural Programming Architectures Generalize via Recursion","created":"2017-04-21","cited_by_count":35},{"id":"2011.05268","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","created":"2020-10-24","cited_by_count":30},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28},{"id":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25},{"id":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23},{"id":"2112.06204","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","created":"2021-12-12","cited_by_count":16},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15}],"next_cursor":null}