> "Is {sentence_a} similar to {sentence_b}?"
I also find this methods powerful. I see more and more software is getting outsourced into LLM judgements/prompts.
I also find this methods powerful. I see more and more software is getting outsourced into LLM judgements/prompts.
Embedding models usually have fewer parameters than the LLMs, and once we index the documents, their retrieval is also pretty fast. Using LLM as a judge makes sense, but only on a limited scale.