Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs

arXiv:2403.05434v1 Announce Type: new
Abstract: Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages(HRLs). A few of them have been trained in low-resource languages (LRLs) and give decent performance. Owing to the prohibitive costs of training LLMs, they are usually used as a network service, with the client charged by the count of input and output tokens. The number of tokens strongly depends on the script and language, as well as the LLM's sub-word vocabulary. …

abstract arxiv commercial cost costs cs.cl few-shot inference language language models languages large language large language models llms low network optimization performance processing quality service tasks them training training llms type