{"total":14,"rows":[{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2412.09460","title":"The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspective","created":"2024-12-12","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2512.20823","title":"NotSoTiny: A Large, Living Benchmark for RTL Code Generation","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2601.14698","title":"ClaimDB: A Fact Verification Benchmark over Large Structured Data","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2505.24263","title":"Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation","created":"2025-05-30","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":"2505.23598","title":"LLM Performance for Code Generation on Noisy Tasks","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.23358","title":"Text-to-SQL Task-oriented Dialogue Ontology Construction","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2601.14994","title":"Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.23517","title":"Beyond Accuracy: Introducing a Symbolic-Mechanistic Approach to Interpretable Evaluation","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2505.13249","title":"RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2603.20965","title":"Learning to Aggregate Zero-Shot LLM Agents for Corporate Disclosure Classification","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2608.07914","title":"When Is Benchmark Contamination Detectable? Information Limits and Power-Calibrated Audits","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}