Cobus Greyling (5)

LLM Alignment, Hallucination & Misinformation

This study yet again shows the importance of data discovery, data design & data delivery to the LLM; all with human...

A New Prompt Technique From DeepMind Called Optimisation by PROmpting (OPRO)

A number of advancements have been made in the area of prompting techniques, enabling LLMs to significantly improved...

How Should Large Language Models Be Evaluated?

A while ago Tianjin University released a study, which defined a LLM model evaluation and implementation taxonomy.

DialogGPT

DialogGPT addresses the complexities of managing natural, context-rich conversations at scale within enterprise...

The Shifting Vocabulary of AI (Updated)

The vocabulary in Generative AI and Conversational AI is evolving rapidly, introducing new terms that shape how we...

Can Minor Document Typos Comprehensively Disrupt RAG Retriever & Reader Components?

Retrieval-Augmented Generation (RAG) is effective in leveraging LLM in-context learning (ICL) capabilities.

But are we...

Data Design For Fine-Tuning To Improve Small Language Model Behaviour

Teaching Small Language Models to Self-Correct & Reason by using creative data formats for fine-tuning data. Via Prompt...

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...