Improving LLMs with a knowledge from databases

TL;DR

This paper introduces a novel method that enhances large language models' answers by integrating a ruleset derived from databases using interpretable association rules, improving accuracy and safety.

Contribution

The paper proposes a new approach combining association rule mining with RAG techniques to improve LLM responses based on structured data.

Findings

Significant improvement over ChatGPT in dataset-based questions

Method effectively integrates rules into LLMs via RAG

Potential for further enhancements with additional patterns

Abstract

Large language models (LLMs) are achieving significant progress almost every moment now. Many advanced techniques have been introduced and widely accepted, like retrieval-augmentation generation (RAG), agents, and tools. Tools can query the database to answer questions from structured data files or perform groupings or other statistics. This unlocks huge opportunities, such as it can answer any question, but also poses threats, such as safety, because there is no control over the commands that are created. We would like to discuss whether we can create a new method that improves answers based on dataset/database via some interpretable ML methods, namely enhanced association rules. The advantage would be if the method can be also used in some safe technique like RAG. Association rules have a sound history. Since the introduction of CN2 and aproiri, many enhancements have been made. In parallel, enhanced association rules have been introduced and evolved over the last 40 years. The general problem is typically that there are too many rules. There are some techniques for handling it, but when LLM emerged, it turned out to be the best use case for the RAG technique for LLMs. We proposed a method that generates a ruleset based on defined knowledge patterns, then converts rules into text form via a rule-to-text converter, and includes the result as an RAG into LLM. We compared this method with ChatGPT (even with using agents) and we have discovered a significant improvement in answering questions based on the dataset. We have also tried several strategies how much rules to generate. We found this improvement interesting. Moreover, it can also be improved in many ways as future work, like incorporating other patterns, the use of rule mining as an agent, and many others.