Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits

arXiv:2403.07213v1 Announce Type: new
Abstract: Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to choose the best model among a diverse set while balancing task reward and exploration cost. Organizations faces decisions like whether to employ a costly API-based LLM or a locally finetuned small LLM, weighing cost against performance. …

abstract adoption applications arxiv attention chatbots complexity convergence cs.lg llm llms model selection recommendations scale search stat.ml type web