A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems
This finding questions fundamental aspects of RAG systems, potentially impacting AI practitioners relying on instructed models for enhanced performance.
The study found that base large language models outperform instructed models by 20% on average in Retrieval Augmented Generation tasks, challenging assumptions about the superiority of instructed models.
Retrieval Augmented Generation (RAG) represents a significant advancement in artificial intelligence combining a retrieval phase with a generative phase, with the latter typically being powered by large language models (LLMs). The current common practices in RAG involve using "instructed" LLMs, which are fine-tuned with supervised training to enhance their ability to follow instructions and are aligned with human preferences using state-of-the-art techniques. Contrary to popular belief, our study demonstrates that base models outperform their instructed counterparts in RAG tasks by 20% on average under our experimental settings. This finding challenges the prevailing assumptions about the superiority of instructed LLMs in RAG applications. Further investigations reveal a more nuanced situation, questioning fundamental aspects of RAG and suggesting the need for broader discussions on the topic; or, as Fromm would have it, "Seldom is a glance at the statistics enough to understand the meaning of the figures".