费半天劲加了数据库之后,效果也没比GPT4好很多,性价比可以说非常低。
费半天劲加了数据库之后,效果也没比GPT4好很多,性价比可以说非常低。
另外 bing 怎么连 3.5 都不如呢?不是号称是4吗 hhh
elvis: Nice paper showing how retrieval-augmented LLMs can improve accuracy on biomedical questions.
- The retrieval-enhanced model outperforms more general-purpose LLMs (GPT-4 & GPT-3.5) in accuracy and relevance.
- This approach also helps reduce hallucination and irrelevant outputs…