Augmenting LLMs with databases is great, but there are major flaws in that approach

"Augmenting LLMs with databases is great, but there are major flaws in that approach! We see a lot of debates around fine-tuning versus Retriever Augmented Generation (RAG) with LLMs these days. Augmenting LLMs with small additional data is better served by RAG, but it is important to understand the shortcomings of that approach!

In ABN, during our work on MyAi Buratino, we needed to deal with multiple problems with the current LLM quality issues. The field is simply too early for our expectation and for enterprise use. Therefore, ABN needed to spend significant effort to build a lot on top of it.

The idea with RAG is to encode the data you want to expose to your LLM into embeddings and index that data into a vector database. When a user asks a question, it is converted to an embedding, and we can use it to search for similar embeddings in the database. Once we found similar embeddings, we construct a prompt with the related data to provide context for an LLM to answer the question. Similarity here is usually measured using the cosine similarity metric.

The first problem is that a question is usually not semantically similar to its answers. At least, it is possible for the search to retrieve documents containing the same words as the question or that are used in the same context without providing relevant information to answer the question. Because the search retrieves the most similar documents to the question, depending on the data, too many irrelevant documents may show higher cosine similarity than the documents actually containing the answer.

To be fair, high cosine similarity does not exactly translate to semantic similarity with Transformers. High cosine similarity can also capture the high co-occurrence of 2 different terms within the same sub-text of the training data, which often happens for a specific question and its related answer.

Another problem may be related to the way the data has been indexed. If the data have been broken down into big chunks of text, then it is likely to contain multiple different and unrelated information within each chunk. If you perform a similarity search on that data, the pertinent information may be diluted, and the search may return irrelevant documents instead. It is important to break down the data so that each chunk contains no more than a few paragraphs to ensure more ""uniqueness"" in the concepts developed in each text.

With the RAG approach, it is very important to limit the type of questions we ask the LLM. If we ask questions that require aggregating data all over the database, the answers are most likely going to be wrong, but the LLM won't be able to know that. If the right information is local to one or a few documents, a similarity search may find it. However, if the information requires scanning all the documents to find the answer, a similarity search won't find it. Imagine each document is dated, and we ask, ""What is the earliest document?"". In that case, we can only know the answer if we scan the entire database, and a similarity search won't be helpful. "

Author

AiUTOMATING PEOPLE, ABN ASIA was founded by people with deep roots in academia, with work experience in the US, Holland, Hungary, Japan, South Korea, Singapore, and Vietnam. ABN Asia is where academia and technology meet opportunity. With our cutting-edge solutions and competent software development services, we're helping businesses level up and take on the global scene. Our commitment: Faster. Better. More reliable. In most cases: Cheaper as well.

Feel free to reach out to us whenever you require IT services, digital consulting, off-the-shelf software solutions, or if you'd like to send us requests for proposals (RFPs). You can contact us at [email protected]. We're ready to assist you with all your technology needs.

© ABN ASIA