{"total":19,"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":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2509.10179","title":"Benchmark of stylistic variation in LLM-generated texts","created":"2025-09-12","cited_by_count":7,"area":null},{"id":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2508.20452","title":"Evaluating Differentially Private Generation of Domain-Specific Text","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2503.18313","title":"Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2502.06655","title":"Unbiased Evaluation of Large Language Models from a Causal Perspective","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2605.19999","title":"LLM Benchmark Datasets Should Be Contamination-Resistant","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2501.13983","title":"AdEval: Alignment-based Dynamic Evaluation to Mitigate Data Contamination in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2510.19036","title":"From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2605.23628","title":"How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2608.14065","title":"Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2508.20275","title":"A Systematic Review on the Generative AI Applications in Human Medical Genomics","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2603.21636","title":"Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.14164","title":"Unsteady Metrics and Benchmarking Cultures of AI Model Builders","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2609.26023","title":"Reciprocal Collaboration: how lessons from convergence in GLAMs can enhance interdisciplinary AI research","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}