{"total":15,"rows":[{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372,"area":null},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"area":null},{"id":"2404.09135","title":"Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions","created":"2024-04-14","cited_by_count":18,"area":null},{"id":"2311.13628","title":"Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2306.01549","title":"Evaluating Machine Translation Quality with Conformal Predictive Distributions","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2301.03403","title":"A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2512.18028","title":"Embodied4C: Measuring What Matters for Embodied Vision-Language Navigation","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2406.06569","title":"Enhancing Clinical Documentation with Synthetic Data: Leveraging Generative Models for Improved Accuracy","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2508.10161","title":"LaajMeter: A Framework for LaaJ Evaluation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2605.17503","title":"RAG-based EEG-to-Text Translation Using Deep Learning and LLMs","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2403.16393","title":"Concurrent Linguistic Error Detection (CLED): a New Methodology for Error Detection in Large Language Models","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2511.22313","title":"Sentiment Analysis Of Shopee Product Reviews Using Distilbert","created":"2025-11-27","cited_by_count":0,"area":null}],"next_cursor":null}