ChatGPT vs ChatDKG

A glimpse at the future of decentralized Retrieval-Augmented Generation (RAG)

The comparison between ChatGPT4 by OpenAI and ChatDKG by OriginTrail sheds light on the performance of generative AI models in addressing specific queries. This head-to-head uses ChatGPT as an example but the same principles apply to other LLMs such has Google Gemini, Claude, Grok and so on.

When prompted with the question:

"What was the composition of Nike's global corporate leadership in terms of gender in 2021?"

ChatGPT response was characterized as vague, lengthy, and lacking in directness.

Conversely, ChatDKG provided a concise and factually precise answer sourced from the OriginTrail Decentralized Knowledge Graph, ensuring verifiability and accuracy:

The framework facilitating this accuracy, termed Decentralized Retrieval-Augmented Generation (RAG), allows AI models to access external knowledge bases for grounded responses. Meta introduced a similar concept in a 2020 paper titled "Retrieval-Augmented Generation," aiming to expand LLMs' knowledge beyond training data.

To enhance transparency, inclusivity and authenticity with ensured information provenance in RAG, OriginTrail DKG serves as a foundation for decentralized Internet, fostering more capable and precise, hallucinaton-proof AI solutions.

Returning to the query about Nike's corporate leadership composition, OriginTrail DKG traces the information lineage and facilitates further exploration by using the DKG Explorer.

Source

The answer provided by Decentralized RAG accurately reflects Nike's gender composition in 2021, sourced from the FY21 Nike, Inc. Impact Report accessible via the Wikirate open data platform providing open access to sustainability reports corporations publish annually.

OriginTrail DKG's utility extends beyond enterprise knowledge exchange, fostering trust and transparency across industries. As it evolves, OriginTrail aims to connect global knowledge repositories, driving precise and inclusive AI through Decentralized RAG.