{"total":18,"rows":[{"id":"2411.09105","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","created":"2024-11-14","cited_by_count":10,"area":null},{"id":"2505.22830","title":"What Has Been Lost with Synthetic Evaluation?","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2502.01683","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2510.01474","title":"AIReg-Bench: Benchmarking Language Models That Assess AI Regulation Compliance","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2505.20738","title":"Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2504.02293","title":"Breaking the Silence: A Dataset and Benchmark for Bangla Text-to-Gloss Translation","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2509.26600","title":"When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2601.08847","title":"Scalable and Reliable Evaluation of AI Knowledge Retrieval Systems: RIKER and the Coherent Simulated Universe","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2508.04337","title":"Modelling and Classifying the Components of a Literature Review","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2511.14774","title":"LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2501.15922","title":"SkillScope: A Tool to Predict Fine-Grained Skills Needed to Solve Issues on GitHub","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2510.04641","title":"Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2604.14163","title":"SeaAlert: Robust Severity Classification and LLM-Based Information Extraction for Noisy Maritime Distress Communications","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.21031","title":"Synthetic Data in Education: Empirical Insights from Traditional Resampling and Deep Generative Models","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.06835","title":"On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.21074","title":"PromptResponse: Optimizing Prompts for LLM Coding Tasks","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00005","title":"Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models","created":"2026-07-11","cited_by_count":0,"area":null}],"next_cursor":null}