{"total":22,"rows":[{"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":"2406.14991","title":"SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation","created":"2024-06-21","cited_by_count":111,"area":null},{"id":"2410.11076","title":"PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries","created":"2024-10-14","cited_by_count":19,"area":null},{"id":"2407.09025","title":"SpreadsheetLLM: Encoding Spreadsheets for Large Language Models","created":"2024-07-12","cited_by_count":17,"area":null},{"id":"2411.19504","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","created":"2024-11-29","cited_by_count":17,"area":null},{"id":"2506.13405","title":"RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2403.13583","title":"CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2510.09671","title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2412.10104","title":"RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2503.04396","title":"TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2410.10270","title":"QUIS: Question-guided Insights Generation for Automated Exploratory Data Analysis","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2412.17867","title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2505.17149","title":"Large Language Models for Predictive Analysis: How Far Are They?","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2403.02962","title":"WikiTableEdit: A Benchmark for Table Editing by Natural Language Instruction","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2501.01014","title":"MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2505.10714","title":"GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2404.08480","title":"Using ChatGPT for Data Science Analyses","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2412.20072","title":"Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2511.17559","title":"SCARE: A Benchmark for SQL Correction and Question Answerability Classification for Reliable EHR Question Answering","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2604.17944","title":"ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.22762","title":"Behavioral Intelligence Platforms: From Event Streams to Autonomous Insight via Probabilistic Journey Graphs, Behavioral Knowledge Extraction, and Grounded Language Generation","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.21338","title":"Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":null}