Cobus Greyling (2)

A Study Comparing RAG & Fine-Tuning For Knowledge Base Use-Cases

Cobus Greyling

The selection of technology should be driven primarily by the requirements and goals of a particular use-case or...

RAT — Retrieval Augmented Thoughts

Cobus Greyling

Let me first start with a few general observations…

There is a tension between achieving efficiency within...

A Short History Of RAG

Cobus Greyling

One of the most popular themes currently around Large Language Models is the idea of Retrieval Augmented Generation...

Chain-of-Instructions (CoI) Fine-Tuning

Cobus Greyling

This approach draws inspiration from Chain-of-Thought (CoT) prompting which generates step-by-step rationales from...

Performing Multiple LLM Calls & Voting On The Best Result Are Subject To Scaling Laws

Cobus Greyling

More LLM calls enhance performance on easy queries but diminish it on hard ones.

So what scaling laws can be...

Exploring the Purpose, Power & Potential of Small Language Models (SLMs)

Cobus Greyling

A number of very capable Small Language Models (SLMs) have been open-sourced recently. In this article you will find...

Self-Reflective Retrieval-Augmented Generation (SELF-RAG)

Cobus Greyling

The SELF-RAG framework trains a single arbitrary language model to adaptively retrieve passages on-demand.To generate...

Prompt-RAG

Cobus Greyling

Vector Embedding Free Retrieval-Augmented Generation

While Prompt-RAG does come with its limitations, it can...

Please Stop Saying Long Context Windows Will Replace RAG

Cobus Greyling

And I’m curious to know if anyone has innovative approaches to using long context windows efficiently?

Long Context...

LLMs Training SLMs

Cobus Greyling

Research from Microsoft Research shows how they used LLMs to train SLMs without any RLHF…

The primary focus in training...

Kore.ai Technical Blog

A Study Comparing RAG & Fine-Tuning For Knowledge Base Use-Cases

RAT — Retrieval Augmented Thoughts

A Short History Of RAG

Chain-of-Instructions (CoI) Fine-Tuning

This approach draws inspiration from Chain-of-Thought (CoT) prompting which generates step-by-step rationales from...

Performing Multiple LLM Calls & Voting On The Best Result Are Subject To Scaling Laws

More LLM calls enhance performance on easy queries but diminish it on hard ones.

So what scaling laws can be...

Exploring the Purpose, Power & Potential of Small Language Models (SLMs)

A number of very capable Small Language Models (SLMs) have been open-sourced recently. In this article you will find...

Self-Reflective Retrieval-Augmented Generation (SELF-RAG)

Prompt-RAG

Vector Embedding Free Retrieval-Augmented Generation

Please Stop Saying Long Context Windows Will Replace RAG

And I’m curious to know if anyone has innovative approaches to using long context windows efficiently?

LLMs Training SLMs

Research from Microsoft Research shows how they used LLMs to train SLMs without any RLHF…

Leave Comment

Products

XO Capabilities

Solutions

Industries

Developers

RESOURCES

Support

Let’s work together