{"list":"other","total":53,"rows":[{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"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":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"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":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"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":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232},{"id":"2312.11370","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","created":"2023-12-18","cited_by_count":210},{"id":"2402.11684","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","created":"2024-02-18","cited_by_count":205},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"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":"2010.12773","title":"Structure-Grounded Pretraining for Text-to-SQL","created":"2020-10-24","cited_by_count":126},{"id":"2412.14167","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation","created":"2024-12-18","cited_by_count":108},{"id":"1908.01839","title":"Text-to-SQL Generation for Question Answering on Electronic Medical Records","created":"2019-07-28","cited_by_count":77},{"id":"2109.05153","title":"Natural SQL: Making SQL Easier to Infer from Natural Language Specifications","created":"2021-09-11","cited_by_count":68},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","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":"2406.07502","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","created":"2024-06-11","cited_by_count":43},{"id":"2406.19976","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","created":"2024-06-28","cited_by_count":37},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36},{"id":"2402.16671","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","created":"2024-02-26","cited_by_count":29},{"id":"2410.07113","title":"Personalized Visual Instruction Tuning","created":"2024-10-09","cited_by_count":24},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23},{"id":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18},{"id":"2408.12733","title":"SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging","created":"2024-08-22","cited_by_count":16},{"id":"2104.05819","title":"Learning from Executions for Semantic Parsing","created":"2021-04-12","cited_by_count":7},{"id":"2410.18406","title":"MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases","created":"2024-10-24","cited_by_count":6},{"id":"2403.08375","title":"Translating between SQL Dialects for Cloud Migration","created":"2024-03-13","cited_by_count":4}],"next_cursor":null}