Feb. 12, 2024, 5:43 a.m. | Murong Yue Jie Zhao Min Zhang Liang Du Ziyu Yao

cs.LG updates on arXiv.org arxiv.org

Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services. In this paper, we are motivated to study building an LLM cascade to save the cost of using LLMs, particularly for performing reasoning (e.g., mathematical, causal) tasks. Our cascade pipeline follows the intuition that simpler questions can be addressed by a weaker but more affordable LLM, whereas only the …

api building cost cs.ai cs.cl cs.lg gpt gpt-4 language language model language models large language large language model large language models llm llms paper performance reasoning save services study tasks thoughts

Research Scholar (Technical Research)

@ Centre for the Governance of AI | Hybrid; Oxford, UK

HPC Engineer (x/f/m) - DACH

@ Meshcapade GmbH | Remote, Germany

Senior Analytics Engineer (Retail)

@ Lightspeed Commerce | Toronto, Ontario, Canada

Data Scientist II, BIA GPS India Operations

@ Bristol Myers Squibb | Hyderabad

Analytics Engineer

@ Bestpass | Remote

Senior Analyst - Data Management

@ Marsh McLennan | Mumbai - Hiranandani