all AI news
Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
March 13, 2024, 4:41 a.m. | Yu Xia, Fang Kong, Tong Yu, Liya Guo, Ryan A. Rossi, Sungchul Kim, Shuai Li
cs.LG updates on arXiv.org arxiv.org
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
More from arxiv.org / cs.LG updates on arXiv.org
Training robust and generalizable quantum models
51 minutes ago |
arxiv.org
Causal Discovery Under Local Privacy
51 minutes ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Consultant Senior Power BI & Azure - CDI - H/F
@ Talan | Lyon, France