"Agentic AI relies on a multitude of technological innovations. One of the most notable is Retrieval-Augmented Generation (RAG), the technique at the core of enabling AI systems to acquire insights from business data. As is often the case, innovation is iterative. The new 'Instructed Retriever' architecture finds up to 70 percent more relevant information than AI with RAG alone could achieve."
"The simplest (and fastest) way for RAG to work is to give an AI model free rein to parse through business data. These models are fast and efficient at this compared to humans. At the same time, the researchers see many shortcomings with such a basic setup. Above all, LLMs often just do not adhere to user instructions. Beyond that rather fundamental problem, AI models regularly fail to grasp the context of their sources very well,"
The Instructed Retriever (IR) is an extension of Retrieval-Augmented Generation (RAG) designed to increase relevance retrieval by up to 70 percent. Databricks conceived IR to mitigate several RAG shortcomings. Basic RAG gives models free rein to parse business data, yielding speed and efficiency but producing inconsistent behavior: LLMs often do not adhere to user instructions, fail to grasp source context in domain-specific data, and cannot reason about outputs before returning them. Multi-step agents add reasoning but reduce speed and consistency. IR remedies many of these issues while remaining largely invisible to end users by steering retrieval toward more relevant, context-aware information.
Read at Techzine Global
Unable to calculate read time
Collection
[
|
...
]