{"total":15,"rows":[{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461,"area":null},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165,"area":null},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2406.00025","title":"SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2506.11887","title":"Cascaded Language Models for Cost-effective Human-AI Decision-Making","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2402.01173","title":"Efficient Prompt Caching via Embedding Similarity","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2310.13561","title":"Cache & Distil: Optimising API Calls to Large Language Models","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2511.16883","title":"PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling","created":"2025-11-21","cited_by_count":4,"area":null},{"id":"2503.17603","title":"A Generative Caching System for Large Language Models","created":"2025-03-22","cited_by_count":3,"area":null},{"id":"2403.13835","title":"SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2509.15515","title":"LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2601.08991","title":"Optimising for Energy Efficiency and Performance in Machine Learning","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2605.17288","title":"When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":null}