{"total":36,"rows":[{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2412.04403","title":"Establishing Task Scaling Laws via Compute-Efficient Model Ladders","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29,"area":null},{"id":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2410.01692","title":"U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2406.09366","title":"Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations","created":"2024-06-13","cited_by_count":8,"area":null},{"id":"2506.19882","title":"Position: Machine Learning Conferences Should Establish a \"Refutations and Critiques\" Track","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2512.08894","title":"Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training","created":"2025-12-09","cited_by_count":6,"area":null},{"id":"2509.24012","title":"Pretraining Scaling Laws for Generative Evaluations of Language Models","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2406.14549","title":"Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2508.18609","title":"Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2502.18339","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.14919","title":"Predicting Task Performance with Context-aware Scaling Laws","created":"2025-10-16","cited_by_count":2,"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":"2601.19831","title":"Neural Neural Scaling Laws","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2606.07616","title":"Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2608.11859","title":"Small-Scale Experiments: Are We There Yet?","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2602.11217","title":"The Magic Correlations: Understanding Knowledge Transfer from Pretraining to Supervised Fine-Tuning","created":"2026-02-11","cited_by_count":1,"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":"2506.03592","title":"From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2603.11001","title":"RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2607.02464","title":"Will Scaling Improve Social Simulation with LLMs?","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.10296","title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.01573","title":"Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.27588","title":"The Capability Manifold and ML Scaling Laws","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.19185","title":"How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}