{"total":25,"rows":[{"id":"2405.17202","title":"Efficient multi-prompt evaluation of LLMs","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2504.02733","title":"Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study","created":"2025-04-03","cited_by_count":17,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2409.12106","title":"Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2406.12319","title":"The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators","created":"2024-06-18","cited_by_count":11,"area":null},{"id":"2512.11437","title":"CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare","created":"2025-12-12","cited_by_count":9,"area":null},{"id":"2505.12837","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2505.14314","title":"Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2506.18756","title":"Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2412.10558","title":"Too Big to Fool: Resisting Deception in Language Models","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2504.18827","title":"Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning","created":"2025-04-26","cited_by_count":2,"area":null},{"id":"2505.14201","title":"FLASH-D: FlashAttention with Hidden Softmax Division","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2601.09724","title":"Syntactic Framing Fragility: An Audit of Robustness in LLM Ethical Decisions","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2506.11017","title":"TeleEval-OS: Performance evaluations of large language models for operations scheduling","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2506.17369","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2609.13824","title":"When Consistency Does Not Mean Reliability: Evaluating Local LLM Judges Against Human Ratings","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2609.34457","title":"ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2509.05375","title":"Characterizing Fitness Landscape Structures in Prompt Engineering","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2510.06834","title":"Vectorized FlashAttention with Low-cost Exponential Computation in RISC-V Vector Processors","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2512.19305","title":"CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2603.21636","title":"Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.07046","title":"An Interpretable and Scalable Framework for Evaluating Large Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.22797","title":"Measuring Behavior Portability in Large Language Models","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}