{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"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":"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":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"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":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"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":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204},{"id":"2207.08143","title":"Can large language models reason about medical questions?","created":"2022-07-17","cited_by_count":194},{"id":"2302.10198","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","created":"2023-02-19","cited_by_count":155},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"id":"2004.04494","title":"MuTual: A Dataset for Multi-Turn Dialogue Reasoning","created":"2020-04-09","cited_by_count":115},{"id":"1809.02922","title":"Transforming Question Answering Datasets Into Natural Language Inference Datasets","created":"2018-09-09","cited_by_count":99},{"id":"2303.07103","title":"Could a Large Language Model be Conscious?","created":"2023-03-04","cited_by_count":73},{"id":"1606.02858","title":"A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task","created":"2016-06-09","cited_by_count":72},{"id":"2307.13692","title":"ARB: Advanced Reasoning Benchmark for Large Language Models","created":"2023-07-25","cited_by_count":60},{"id":"2010.02830","title":"PRover: Proof Generation for Interpretable Reasoning over Rules","created":"2020-10-06","cited_by_count":53},{"id":"1906.06298","title":"Augmenting Neural Networks with First-order Logic","created":"2019-06-14","cited_by_count":51},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43},{"id":"1904.12166","title":"HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning","created":"2019-04-27","cited_by_count":35},{"id":"2305.12147","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","created":"2023-05-20","cited_by_count":31},{"id":"2103.14349","title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","created":"2021-03-26","cited_by_count":28},{"id":"2009.14505","title":"TaxiNLI: Taking a Ride up the NLU Hill","created":"2020-09-30","cited_by_count":27},{"id":"2210.03256","title":"Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation","created":"2022-10-06","cited_by_count":25},{"id":"2011.04864","title":"Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts","created":"2020-11-10","cited_by_count":23},{"id":"2301.11596","title":"ThoughtSource: A central hub for large language model reasoning data","created":"2023-01-27","cited_by_count":23}],"next_cursor":null}