{"list":"other","total":156,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"1801.08163","title":"DVQA: Understanding Data Visualizations via Question Answering","created":"2018-01-24","cited_by_count":340},{"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":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267},{"id":"1803.09473","title":"code2vec: Learning Distributed Representations of Code","created":"2018-03-26","cited_by_count":250},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1609.06038","title":"Enhanced LSTM for Natural Language Inference","created":"2016-09-20","cited_by_count":200},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192},{"id":"1705.00106","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","created":"2017-04-29","cited_by_count":186},{"id":"2005.12592","title":"GECToR -- Grammatical Error Correction: Tag, Not Rewrite","created":"2020-05-26","cited_by_count":177},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147},{"id":"2210.14179","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","created":"2022-10-25","cited_by_count":133},{"id":"1812.05252","title":"Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering","created":"2018-12-13","cited_by_count":114},{"id":"1812.08693","title":"An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation","created":"2018-12-20","cited_by_count":108},{"id":"2106.03830","title":"A Simple Recipe for Multilingual Grammatical Error Correction","created":"2021-06-07","cited_by_count":108},{"id":"1909.01187","title":"Encode, Tag, Realize: High-Precision Text Editing","created":"2019-09-03","cited_by_count":99},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98},{"id":"2304.01746","title":"Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation","created":"2023-04-04","cited_by_count":97},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"2109.03034","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","created":"2021-09-07","cited_by_count":82},{"id":"1910.02893","title":"Parallel Iterative Edit Models for Local Sequence Transduction","created":"2019-10-07","cited_by_count":81},{"id":"2109.05729","title":"CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation","created":"2021-09-13","cited_by_count":81},{"id":"2203.13947","title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","created":"2022-03-26","cited_by_count":80},{"id":"2308.02773","title":"EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education","created":"2023-08-05","cited_by_count":80},{"id":"1704.01792","title":"Neural Question Generation from Text: A Preliminary Study","created":"2017-04-06","cited_by_count":78},{"id":"2303.13648","title":"ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark","created":"2023-03-15","cited_by_count":77},{"id":"1906.08104","title":"EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing","created":"2019-06-19","cited_by_count":63},{"id":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62},{"id":"2305.03453","title":"T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering","created":"2023-05-05","cited_by_count":60},{"id":"2009.11136","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","created":"2020-09-23","cited_by_count":58},{"id":"1811.05632","title":"Translating a Math Word Problem to an Expression Tree","created":"2018-11-14","cited_by_count":57},{"id":"2004.14166","title":"SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check","created":"2020-04-26","cited_by_count":57},{"id":"2301.03270","title":"A Survey of Learning-based Automated Program Repair","created":"2023-01-09","cited_by_count":55},{"id":"2108.06688","title":"Complex Knowledge Base Question Answering: A Survey","created":"2021-08-15","cited_by_count":52},{"id":"1505.01121","title":"Ask Your Neurons: A Neural-based Approach to Answering Questions about Images","created":"2015-05-05","cited_by_count":51},{"id":"1410.8206","title":"Addressing the Rare Word Problem in Neural Machine Translation","created":"2014-10-30","cited_by_count":50},{"id":"1811.00720","title":"Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems","created":"2018-11-02","cited_by_count":49},{"id":"2205.11503","title":"Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models","created":"2022-05-23","cited_by_count":49},{"id":"2308.11148","title":"LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning","created":"2023-08-22","cited_by_count":47},{"id":"2309.08221","title":"Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study","created":"2023-09-15","cited_by_count":44},{"id":"2211.05166","title":"Grammatical Error Correction: A Survey of the State of the Art","created":"2022-11-09","cited_by_count":43},{"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":"1706.02027","title":"Question Answering and Question Generation as Dual Tasks","created":"2017-06-07","cited_by_count":37},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","cited_by_count":33},{"id":"1705.02012","title":"Machine Comprehension by Text-to-Text Neural Question Generation","created":"2017-05-04","cited_by_count":32},{"id":"2210.12484","title":"SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser","created":"2022-10-22","cited_by_count":32},{"id":"1808.07290","title":"The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers","created":"2018-08-22","cited_by_count":31},{"id":"2105.11698","title":"Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting","created":"2021-05-25","cited_by_count":30},{"id":"1609.07197","title":"Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems","created":"2016-09-23","cited_by_count":28},{"id":"2011.13100","title":"Automatic Distractor Generation for Multiple Choice Questions in Standard Tests","created":"2020-11-26","cited_by_count":26},{"id":"2203.14187","title":"Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization","created":"2022-03-27","cited_by_count":26},{"id":"2012.10582","title":"Learning by Fixing: Solving Math Word Problems with Weak Supervision","created":"2020-12-19","cited_by_count":25},{"id":"2102.00781","title":"Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays","created":"2021-02-01","cited_by_count":25},{"id":"1809.02768","title":"Generating Distractors for Reading Comprehension Questions from Real Examinations","created":"2018-09-08","cited_by_count":24},{"id":"1805.09701","title":"R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering","created":"2018-05-24","cited_by_count":23},{"id":"1910.09342","title":"Domain-agnostic Question-Answering with Adversarial Training","created":"2019-10-21","cited_by_count":22},{"id":"2008.01441","title":"Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring","created":"2020-08-04","cited_by_count":22},{"id":"2010.05384","title":"A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies","created":"2020-10-12","cited_by_count":22},{"id":"2106.04262","title":"Question Generation for Adaptive Education","created":"2021-06-08","cited_by_count":22},{"id":"2311.14109","title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","created":"2023-11-23","cited_by_count":22},{"id":"2310.08395","title":"Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation","created":"2023-10-12","cited_by_count":21}],"next_cursor":"100"}