LLM Enhancer: Merged Approach using Vector Embedding for Reducing Large Language Model Hallucinations with External Knowledge
This addresses the issue of inaccurate information in LLMs for real-world critical applications, though it appears incremental as it builds on existing methods for knowledge integration.
The paper tackles the problem of hallucinations in large language models by introducing the LLM Enhancer system, which integrates multiple online sources to enhance data accuracy, resulting in reduced hallucinations while preserving response naturalness and accuracy.
Large Language Models (LLMs), such as ChatGPT, have demonstrated the capability to generate human like, natural responses across a range of tasks, including task oriented dialogue and question answering. However, their application in real world, critical scenarios is often hindered by a tendency to produce inaccurate information and a limited ability to leverage external knowledge sources. This paper introduces the LLM ENHANCER system, designed to integrate multiple online sources such as Google, Wikipedia, and DuckDuckGo to enhance data accuracy. The LLMs employed within this system are open source. The data acquisition process for the LLM ENHANCER system operates in parallel, utilizing custom agent tools to manage the flow of information. Vector embeddings are used to identify the most pertinent information, which is subsequently supplied to the LLM for user interaction. The LLM ENHANCER system mitigates hallucinations in chat based LLMs while preserving response naturalness and accuracy.