One of the main limiting factors of knowledge graphs was understanding schema and creation of queries to extract relevant information. When we combine LLMs with GraphRAG we can use natural language to answer many questions. What if we want to answer more complex questions? 

Such as: 

What highly-rated movies (IMDB rating above 7.5) has Nicholas Burke rated, what are their genres, who acted in them, who directed them, and what other exceptional movies (IMDB rating above 9) have those actors appeared in?

1. We cannot retrieve documents from a vector store and send it to LLM because there are too many of them. Also there is not a single document that contains all the information.

2. If we use finetuned LLM we will get hallucinations or stale information.

3. GraphRAG will give us summaries of related information but the actual answer can be hidden in the summaries or not be captured at all.

4. If we naively generate graph query using LLM to answer complex multihop questions we will get very fragile results. These queries suffer from missing links and inconsistencies of the knowledge graphs. 

....

Retrieval Augmented Generation (RAG) techniques help reduce hallucinations in large language models (LLMs). RAG retrieves text based on semantic similarity, though it may not directly answer complex queries where specific details aren't explicitly mentioned in the dataset.

Knowledge Graphs (KGs) offer structured and explicit representations of knowledge, enhancing the reasoning capabilities of LLMs. However, creating and maintaining KGs required significant human effort and domain knowledge, which poses challenges for scaling and usage. Here, we evaluate the automatic creation of KGs from web pages.

Previously, utilizing KGs required proficiency in graph query languages such as Cypher, Gremlin, SPARQL, or RDF. This is no longer necessary, as LLMs can now generate the required queries with the correct schema and process the query results, providing users with a natural language interface to interact with KGs.

....

AI assistants need access to high-quality corporate data to effectively automate routine business tasks. This requirement applies to data used for training, fine-tuning, and inference in Retrieval-Augmented Generation (RAG). 

A large amount of work still remains, including data labeling

....

It verifies facts before presenting them to the user. It will work with the latest information and double-check it against relevant sources such as wikipedia or published papers.

If it generates ideas or concepts from other documents, It maintains a citation list and verifies primary sources to avoid mistakes.

It adheres to the theme and writing style of generated content requested by the user. 

....