{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"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":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"1812.05271","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","created":"2018-12-13","cited_by_count":381},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270},{"id":"1708.08559","title":"DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars","created":"2017-08-28","cited_by_count":251},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2308.13067","title":"Causal Parrots: Large Language Models May Talk Causality But Are Not Causal","created":"2023-08-24","cited_by_count":150},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2306.05836","title":"Can Large Language Models Infer Causation from Correlation?","created":"2023-06-09","cited_by_count":146},{"id":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72},{"id":"1412.7449","title":"Grammar as a Foreign Language","created":"2014-12-23","cited_by_count":70},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63},{"id":"2307.13692","title":"ARB: Advanced Reasoning Benchmark for Large Language Models","created":"2023-07-25","cited_by_count":60},{"id":"2203.00112","title":"GraphWorld: Fake Graphs Bring Real Insights for GNNs","created":"2022-02-28","cited_by_count":56},{"id":"1709.07432","title":"Dynamic Evaluation of Neural Sequence Models","created":"2017-09-21","cited_by_count":55},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53},{"id":"2212.02774","title":"Adaptive Testing of Computer Vision Models","created":"2022-12-06","cited_by_count":39},{"id":"2308.00304","title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","created":"2023-08-01","cited_by_count":33},{"id":"2309.08632","title":"Pretraining on the Test Set Is All You Need","created":"2023-09-13","cited_by_count":33},{"id":"2105.00828","title":"Memorisation versus Generalisation in Pre-trained Language Models","created":"2021-04-16","cited_by_count":32},{"id":"2205.06153","title":"TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding","created":"2022-05-12","cited_by_count":15},{"id":"1912.02367","title":"Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation","created":"2019-12-05","cited_by_count":1}],"next_cursor":null}