Cobus Greyling

T-RAG = RAG + Fine-Tuning + Entity Detection

The T-RAG approach is premised on combining RAG architecture with an open-source fine-tuned LLM and an entities tree...

Beyond Chain-of-Thought LLM Reasoning

This approach can be implemented on a prompt level and does not require any dedicated frameworks or pre-processing.

Comparing Human, LLM & LLM-RAG Responses

A fairly recent study, focused on the healthcare & preoperative medicine compared expert human feedback with LLM...

Craft Successful Conversational User Interfaces: Align User Intent With Developed Intent

In this article I illustrate how to achieve intent alignment by making use of the Kore.ai XO Platform Intent Discovery...

A Benchmark for Verifying Chain-Of-Thought

A Chain-of-Thought is only as strong as its weakest link; a recent study from Google Research created a benchmark for...

Seven RAG Engineering Failure Points

Retrieval-Augmented Generation (RAG) systems remains a compelling solution to the challenge of relevant up-to-date...

UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue

This study explores how the RAG process can be decomposed, adding elements like multi-document retrieval, memory and...

Chain-of-Symbol Prompting (CoS) For Large Language Models

LLMs need to understand a virtual spatial environment described through natural language while planning & achieving...

Concise Chain-of-Thought (CCoT) Prompting

Traditional CoT comes at a cost of increased output token usage, CCoT prompting is a prompt-engineering technique which...

Understanding LLM User Experience & Expectation

This study surfaces valuable insights into the frequency of LLM use together with user intents, expectations and...