{"list":"other","total":135,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"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":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"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":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"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":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2005.08314","title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","created":"2020-05-17","cited_by_count":398},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385},{"id":"2305.09645","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","created":"2023-05-16","cited_by_count":343},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"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":"2302.05965","title":"RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL","created":"2023-02-12","cited_by_count":195},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187},{"id":"1909.05378","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","created":"2019-09-11","cited_by_count":185},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185},{"id":"2009.13845","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","created":"2020-09-29","cited_by_count":171},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169},{"id":"2405.16755","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","created":"2024-05-27","cited_by_count":169},{"id":"2307.07306","title":"C3: Zero-shot Text-to-SQL with ChatGPT","created":"2023-07-14","cited_by_count":164},{"id":"2312.11242","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","created":"2023-12-18","cited_by_count":164},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154},{"id":"1906.02285","title":"SParC: Cross-Domain Semantic Parsing in Context","created":"2019-06-05","cited_by_count":144},{"id":"1711.04436","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","created":"2017-11-13","cited_by_count":135},{"id":"2010.12773","title":"Structure-Grounded Pretraining for Text-to-SQL","created":"2020-10-24","cited_by_count":126},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"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":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111},{"id":"2106.01065","title":"Towards Robustness of Text-to-SQL Models against Synonym Substitution","created":"2021-06-02","cited_by_count":110},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106},{"id":"2405.07467","title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","created":"2024-05-13","cited_by_count":105},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101},{"id":"2403.05156","title":"On Protecting the Data Privacy of Large Language Models (LLMs): A Survey","created":"2024-03-08","cited_by_count":96},{"id":"2301.07507","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","created":"2023-01-18","cited_by_count":93},{"id":"2109.05157","title":"Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization","created":"2021-09-11","cited_by_count":92},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84},{"id":"2406.01265","title":"The Dawn of Natural Language to SQL: Are We Fully Ready?","created":"2024-06-03","cited_by_count":79},{"id":"2403.00835","title":"CLLMs: Consistency Large Language Models","created":"2024-02-28","cited_by_count":72},{"id":"2305.14215","title":"Exploring Chain-of-Thought Style Prompting for Text-to-SQL","created":"2023-05-23","cited_by_count":69},{"id":"2310.17342","title":"ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought","created":"2023-10-26","cited_by_count":65},{"id":"2004.03125","title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","created":"2020-04-07","cited_by_count":63},{"id":"2010.11246","title":"On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries","created":"2020-10-21","cited_by_count":60},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59},{"id":"2305.11853","title":"How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings","created":"2023-05-19","cited_by_count":58},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53},{"id":"2208.13629","title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions","created":"2022-08-29","cited_by_count":52},{"id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","created":"2023-04-28","cited_by_count":52},{"id":"2308.12060","title":"FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering","created":"2023-08-23","cited_by_count":51},{"id":"2405.15307","title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","created":"2024-05-24","cited_by_count":50},{"id":"2208.10099","title":"Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect","created":"2022-08-22","cited_by_count":47},{"id":"2305.12586","title":"Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies","created":"2023-05-21","cited_by_count":45},{"id":"2402.01117","title":"DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models","created":"2024-02-02","cited_by_count":45},{"id":"2310.08975","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","created":"2023-10-13","cited_by_count":44},{"id":"2401.14939","title":"Macro Graph Neural Networks for Online Billion-Scale Recommender Systems","created":"2024-01-26","cited_by_count":40},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39},{"id":"2402.14672","title":"Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments","created":"2024-02-22","cited_by_count":39}],"next_cursor":"100"}