Cobus Greyling

Improve Conversational UIs Using Social Intelligence

For Conversational User Interfaces to improve, the reliance on social intelligence will need to be leveraged. Many now...

Agentic Search-Augmented Factuality Evaluator (SAFE) For LLMs

This study demonstrates that an LLM agent can outperform crowdsourced human annotators…

FaaF: Facts As A Function For Evaluating RAG

There has been instances where another Language Model is used to vet the RAG output, which fails to detect incorrect...

Disambiguation: Dynamic Context For Effective RAG Question Suggestions

This approach reminds of a technique initially implemented by IBM Watson called disambiguation. Where ambiguous input...

FIT-RAG

FIT-RAG: Are RAG Architectures Settling On A Standardised Approach?

As RAG is being used, vulnerabilities are emerging...

Challenges In Adopting Retrieval-Augmented Generation Solutions

I have thoroughly examined some of the recent academic papers on RAG (Retrieval-Augmented Generation) and have...

Adaptive-RAG

It is evident that there needs to be a balance between query time, quality in terms of performance, but also efficiency.

Large Language Models Excel At In-Context Learning (ICL)

Studies have shown that, when supplied with a contextual reference at Inference, LLMs opt to make use of the contextual...

Retrieval Augmented Fine-Tuning (RAFT)

Adapting Language Model to Domain Specific RAG...

Using RAFT, when presented with a question and a batch of retrieved...

DRAGIN: Dynamic RAG Based On Real-Time Information Needs Of LLMs

A study introduced a novel approach to RAG but more importantly the study highlighted a number of shortcomings of...