{"total":20,"rows":[{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2605.05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2510.07959","title":"DISCO: Diversifying Sample Condensation for Efficient Model Evaluation","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2603.21840","title":"Select, Label, Evaluate: Active Testing in NLP","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2606.03330","title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2603.02029","title":"Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.07726","title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2602.15327","title":"Prescriptive Scaling Reveals the Evolution of Language Model Capabilities","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.24999","title":"Efficient Detection of Bad Benchmark Items with Novel Scalability Coefficients","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2606.01400","title":"Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.05029","title":"Validity Threats for Foundation Model Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09878","title":"FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.21839","title":"Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.27023","title":"BayesAME: Bayesian Active Model Evaluation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.20758","title":"Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.18248","title":"Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20099","title":"EvalBuilder: Can LLMs Build Efficient Benchmarks?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}