{"list":"other","total":139,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"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":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"1803.06643","title":"The Web as a Knowledge-base for Answering Complex Questions","created":"2018-03-18","cited_by_count":410},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"1911.03891","title":"Social Bias Frames: Reasoning about Social and Power Implications of Language","created":"2019-11-10","cited_by_count":380},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"1805.01042","title":"Hypothesis Only Baselines in Natural Language Inference","created":"2018-05-02","cited_by_count":295},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2011.00620","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","created":"2020-11-01","cited_by_count":255},{"id":"2010.05953","title":"COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs","created":"2020-10-12","cited_by_count":254},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214},{"id":"1710.06481","title":"Constructing Datasets for Multi-hop Reading Comprehension Across Documents","created":"2017-10-17","cited_by_count":190},{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2205.11822","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","created":"2022-05-24","cited_by_count":159},{"id":"2104.08661","title":"Explaining Answers with Entailment Trees","created":"2021-04-17","cited_by_count":152},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"id":"2005.00646","title":"Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering","created":"2020-05-01","cited_by_count":122},{"id":"1906.02916","title":"Multi-hop Reading Comprehension through Question Decomposition and Rescoring","created":"2019-06-07","cited_by_count":119},{"id":"2002.09758","title":"Unsupervised Question Decomposition for Question Answering","created":"2020-02-22","cited_by_count":118},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109},{"id":"1906.04701","title":"HEAD-QA: A Healthcare Dataset for Complex Reasoning","created":"2019-06-11","cited_by_count":101},{"id":"1906.02900","title":"Compositional Questions Do Not Necessitate Multi-hop Reasoning","created":"2019-06-07","cited_by_count":88},{"id":"1909.04076","title":"Counterfactual Story Reasoning and Generation","created":"2019-09-09","cited_by_count":88},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88},{"id":"2010.05444","title":"OCNLI: Original Chinese Natural Language Inference","created":"2020-10-12","cited_by_count":86},{"id":"1805.06939","title":"Event2Mind: Commonsense Inference on Events, Intents, and Reactions","created":"2018-05-17","cited_by_count":82},{"id":"1908.05852","title":"Reasoning Over Paragraph Effects in Situations","created":"2019-08-16","cited_by_count":79},{"id":"1809.01494","title":"Interpretation of Natural Language Rules in Conversational Machine Reading","created":"2018-08-28","cited_by_count":75},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75},{"id":"1909.04739","title":"WIQA: A dataset for \"What if...\" reasoning over procedural text","created":"2019-09-10","cited_by_count":71},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71},{"id":"2009.07690","title":"Reasoning about Goals, Steps, and Temporal Ordering with WikiHow","created":"2020-09-16","cited_by_count":66},{"id":"2009.00751","title":"Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models","created":"2020-09-01","cited_by_count":65},{"id":"2010.05906","title":"Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning","created":"2020-10-12","cited_by_count":65},{"id":"1905.06933","title":"Dynamically Fused Graph Network for Multi-hop Reasoning","created":"2019-05-16","cited_by_count":63},{"id":"1906.07132","title":"Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA","created":"2019-06-17","cited_by_count":63},{"id":"1804.08117","title":"Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment","created":"2018-04-22","cited_by_count":59},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59},{"id":"1708.01425","title":"The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants","created":"2017-08-04","cited_by_count":56},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54},{"id":"2010.02830","title":"PRover: Proof Generation for Interpretable Reasoning over Rules","created":"2020-10-06","cited_by_count":53},{"id":"2205.12443","title":"Generating Natural Language Proofs with Verifier-Guided Search","created":"2022-05-25","cited_by_count":52},{"id":"1904.12106","title":"Understanding Dataset Design Choices for Multi-hop Reasoning","created":"2019-04-27","cited_by_count":50},{"id":"2010.03274","title":"Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering","created":"2020-10-07","cited_by_count":49},{"id":"2205.05849","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","created":"2022-05-12","cited_by_count":47},{"id":"2005.00771","title":"ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning","created":"2020-05-02","cited_by_count":46},{"id":"1906.06448","title":"Can neural networks understand monotonicity reasoning?","created":"2019-06-15","cited_by_count":45},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45}],"next_cursor":"100"}