{"total":830,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391,"area":null},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902,"area":null},{"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,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562,"area":null},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"area":null},{"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,"area":null},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411,"area":null},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408,"area":null},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388,"area":null},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385,"area":null},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235,"area":null},{"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,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228,"area":null},{"id":"2302.05965","title":"RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL","created":"2023-02-12","cited_by_count":195,"area":null},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175,"area":null},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170,"area":null},{"id":"2405.16755","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","created":"2024-05-27","cited_by_count":169,"area":null},{"id":"2307.07306","title":"C3: Zero-shot Text-to-SQL with ChatGPT","created":"2023-07-14","cited_by_count":164,"area":null},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163,"area":null},{"id":"2402.17944","title":"Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey","created":"2024-02-27","cited_by_count":159,"area":null},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156,"area":null},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156,"area":null},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2209.15189","title":"Learning by Distilling Context","created":"2022-09-30","cited_by_count":138,"area":null},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136,"area":null},{"id":"2408.09174","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","created":"2024-08-17","cited_by_count":128,"area":null},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"area":null},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2406.08426","title":"Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL","created":"2024-06-12","cited_by_count":120,"area":null},{"id":"2106.01093","title":"LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations","created":"2021-06-02","cited_by_count":119,"area":null},{"id":"2303.13547","title":"A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability","created":"2023-03-12","cited_by_count":119,"area":null},{"id":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111,"area":null},{"id":"2106.01065","title":"Towards Robustness of Text-to-SQL Models against Synonym Substitution","created":"2021-06-02","cited_by_count":110,"area":null},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107,"area":null},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106,"area":null},{"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,"area":null},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"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,"area":null},{"id":"2109.05157","title":"Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization","created":"2021-09-11","cited_by_count":92,"area":null},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2205.06983","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","created":"2022-05-14","cited_by_count":85,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85,"area":null},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2403.19318","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","created":"2024-03-28","cited_by_count":77,"area":null},{"id":"2103.12011","title":"Open Domain Question Answering over Tables via Dense Retrieval","created":"2021-03-22","cited_by_count":74,"area":null},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"area":null},{"id":"2106.06600","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","created":"2021-06-11","cited_by_count":71,"area":null},{"id":"2305.15038","title":"Is GPT-4 a Good Data Analyst?","created":"2023-05-24","cited_by_count":70,"area":null},{"id":"2310.09263","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","created":"2023-10-13","cited_by_count":69,"area":null},{"id":"2403.01632","title":"SynCode: LLM Generation with Grammar Augmentation","created":"2024-03-03","cited_by_count":69,"area":null},{"id":"2109.05153","title":"Natural SQL: Making SQL Easier to Infer from Natural Language Specifications","created":"2021-09-11","cited_by_count":68,"area":null},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67,"area":null},{"id":"2207.04154","title":"TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations","created":"2022-07-08","cited_by_count":66,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"area":null},{"id":"2303.18027","title":"Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations","created":"2023-03-31","cited_by_count":63,"area":null},{"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,"area":null},{"id":"2212.09736","title":"Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments","created":"2022-12-19","cited_by_count":57,"area":null},{"id":"2406.13121","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","created":"2024-06-19","cited_by_count":56,"area":null},{"id":"2408.05109","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","created":"2024-08-09","cited_by_count":56,"area":null},{"id":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55,"area":null},{"id":"2404.13207","title":"STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases","created":"2024-04-19","cited_by_count":55,"area":null},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54,"area":null},{"id":"2408.03256","title":"Synthesizing Text-to-SQL Data from Weak and Strong LLMs","created":"2024-08-06","cited_by_count":54,"area":null},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53,"area":null},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53,"area":null},{"id":"2310.18652","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","created":"2023-10-28","cited_by_count":53,"area":null},{"id":"2502.14913","title":"OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment","created":"2025-02-19","cited_by_count":53,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2208.13629","title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions","created":"2022-08-29","cited_by_count":52,"area":null},{"id":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2411.00073","title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","created":"2024-10-31","cited_by_count":52,"area":null},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"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,"area":null},{"id":"2204.08109","title":"ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering","created":"2022-04-17","cited_by_count":48,"area":null},{"id":"2401.04679","title":"RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation","created":"2024-01-09","cited_by_count":48,"area":null},{"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,"area":null},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47,"area":null},{"id":"2505.05568","title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","created":"2025-05-08","cited_by_count":47,"area":null},{"id":"2305.14210","title":"Skill-Based Few-Shot Selection for In-Context Learning","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2301.07695","title":"EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records","created":"2023-01-16","cited_by_count":45,"area":null},{"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,"area":null},{"id":"2306.04743","title":"ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems","created":"2023-06-07","cited_by_count":45,"area":null},{"id":"2402.01117","title":"DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models","created":"2024-02-02","cited_by_count":45,"area":null},{"id":"2106.05006","title":"Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data","created":"2021-06-09","cited_by_count":43,"area":null}],"next_cursor":"100"}