{"total":17,"rows":[{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2308.12261","title":"Prompt2Model: Generating Deployable Models from Natural Language Instructions","created":"2023-08-23","cited_by_count":41,"area":null},{"id":"2305.14947","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","created":"2023-05-24","cited_by_count":34,"area":null},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2407.13696","title":"Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench","created":"2024-07-18","cited_by_count":27,"area":null},{"id":"2310.15147","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","cited_by_count":12,"area":null},{"id":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2407.01300","title":"Collaborative Performance Prediction for Large Language Models","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2510.08730","title":"How Reliable is Language Model Micro-Benchmarking?","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2503.13507","title":"NeurIPS 2023 LLM Efficiency Fine-tuning Competition","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2409.09249","title":"NovAScore: A New Automated Metric for Evaluating Document Level Novelty","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2305.07565","title":"A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2509.23488","title":"Mapping Overlaps in Benchmarks through Perplexity in the Wild","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2402.02548","title":"\"What's my model inside of?\": Exploring the role of environments for grounded natural language understanding","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2411.19689","title":"MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2606.09409","title":"Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}