{"total":32,"rows":[{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853,"area":null},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682,"area":null},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"area":null},{"id":"2102.13004","title":"Towards Unbiased and Accurate Deferral to Multiple Experts","created":"2021-02-25","cited_by_count":72,"area":null},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46,"area":null},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2502.14815","title":"Optimizing Model Selection for Compound AI Systems","created":"2025-02-20","cited_by_count":36,"area":null},{"id":"2402.01742","title":"Towards Optimizing the Costs of LLM Usage","created":"2024-01-29","cited_by_count":33,"area":null},{"id":"2108.07915","title":"Data Pricing in Machine Learning Pipelines","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2104.13621","title":"MLDemon: Deployment Monitoring for Machine Learning Systems","created":"2021-04-28","cited_by_count":14,"area":null},{"id":"2110.03484","title":"Creating Training Sets via Weak Indirect Supervision","created":"2021-10-07","cited_by_count":14,"area":null},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2107.14203","title":"Did the Model Change? Efficiently Assessing Machine Learning API Shifts","created":"2021-07-29","cited_by_count":13,"area":null},{"id":"2102.09127","title":"Efficient Online ML API Selection for Multi-Label Classification Tasks","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2108.06514","title":"Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations","created":"2021-08-14","cited_by_count":5,"area":null},{"id":"2308.03558","title":"Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing","created":"2023-08-07","cited_by_count":4,"area":null},{"id":"2406.14424","title":"CascadeServe: Unlocking Model Cascades for Inference Serving","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2406.04508","title":"OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2504.06307","title":"Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2604.23577","title":"RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization","created":"2026-04-26","cited_by_count":2,"area":null},{"id":"2106.05345","title":"Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2411.09837","title":"Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2607.13048","title":"Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2310.04685","title":"Automatic and Efficient Customization of Neural Networks for ML Applications","created":"2023-10-07","cited_by_count":0,"area":null},{"id":"2607.25068","title":"How Often Should a Recommender Call an LLM? Value-Weighted Routing, Monitoring, and Seasonal Robustness","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.16375","title":"Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.06593","title":"Discovering Translation-Worthy Languages with E-Values","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.15992","title":"Optimal Model Activation Policies for Inference Networks of Large Language Models","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}