{"total":20,"rows":[{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21,"area":null},{"id":"2503.22402","title":"EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2604.25149","title":"Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2608.03451","title":"DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2603.03742","title":"ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.07841","title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2603.12483","title":"Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.16493","title":"NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.17660","title":"TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.23537","title":"SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2512.22744","title":"Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2604.12988","title":"ROSE: An Intent-Centered Evaluation Metric for NL2SQL","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.03465","title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.17649","title":"A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.20489","title":"EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQL","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.23425","title":"TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2609.20842","title":"COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2610.05060","title":"Why, Where, How: Taxonomy-guided Error Grounding for Code Repair in NL2SQL","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}