BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models

arXiv:2403.18365v1 Announce Type: new
Abstract: Large Language Models (LLMs) like ChatGPT and GPT-4 are versatile and capable of addressing a diverse range of tasks. However, general LLMs, which are developed on open-domain data, may lack the domain-specific knowledge essential for tasks in vertical domains, such as legal, medical, etc. To address this issue, previous approaches either conduct continuous pre-training with domain-specific data or employ retrieval augmentation to support general LLMs. Unfortunately, these strategies are either cost-intensive or unreliable in practical …

abstract arxiv blade box chatgpt cs.cl data diverse domain domains etc general gpt gpt-4 however knowledge language language models large language large language models legal llms medical small tasks type