{"list":"other","total":60,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2304.11015","title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","created":"2023-04-21","cited_by_count":477},{"id":"1911.04942","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","created":"2019-11-10","cited_by_count":424},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","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":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228},{"id":"1905.08205","title":"Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation","created":"2019-05-20","cited_by_count":210},{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196},{"id":"2302.05965","title":"RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL","created":"2023-02-12","cited_by_count":195},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139},{"id":"1711.04436","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","created":"2017-11-13","cited_by_count":135},{"id":"2012.12627","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","created":"2020-12-23","cited_by_count":133},{"id":"2303.13547","title":"A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability","created":"2023-03-12","cited_by_count":119},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106},{"id":"2302.13539","title":"Finding Support Examples for In-Context Learning","created":"2023-02-27","cited_by_count":104},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101},{"id":"2205.06983","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","created":"2022-05-14","cited_by_count":85},{"id":"1804.09769","title":"TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation","created":"2018-04-25","cited_by_count":81},{"id":"2009.07396","title":"Grounded Adaptation for Zero-shot Executable Semantic Parsing","created":"2020-09-16","cited_by_count":76},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71},{"id":"2302.11042","title":"In-context Example Selection with Influences","created":"2023-02-21","cited_by_count":61},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51},{"id":"2203.08568","title":"In-Context Learning for Few-Shot Dialogue State Tracking","created":"2022-03-16","cited_by_count":47},{"id":"2206.01335","title":"Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code","created":"2022-06-02","cited_by_count":39}],"next_cursor":null}